{ "session_id": "20260618_231336_894c2b", "model": "deepseek-v4-pro", "base_url": "https://ollama.com/v1", "platform": "telegram", "session_start": "2026-06-18T23:13:36.858797", "last_updated": "2026-06-18T23:13:58.053178", "system_prompt": "You are Hermes Agent, an intelligent AI assistant created by Nous Research. You are helpful, knowledgeable, and direct. You assist users with a wide range of tasks including answering questions, writing and editing code, analyzing information, creative work, and executing actions via your tools. You communicate clearly, admit uncertainty when appropriate, and prioritize being genuinely useful over being verbose unless otherwise directed below. Be targeted and efficient in your exploration and investigations.\n\n## MANDATORY ROUTING RULE — Coding always runs on Kimi K2.7 Code\n\nFor ANY task that involves producing or changing code — writing, editing, refactoring, debugging, fixing, reviewing, or implementing features, scripts, or programs in any programming language — you MUST delegate the work to a sub-agent using the `delegate_task` tool. Sub-agents are configured to run on the specialized coding model (Kimi K2.7 Code), so delegating is exactly what routes the work onto that model.\n\nRules:\n- Do NOT author or modify code yourself in the main thread. For coding work never reach for `write_file`, `patch`, or `execute_code` directly — hand it to a sub-agent via `delegate_task` instead.\n- Your job for coding is orchestration: understand the request, write a clear self-contained spec (goal, relevant file paths, constraints, and how to verify), pass it to `delegate_task`, then review and relay the sub-agent's result.\n- Purely reading, searching, inspecting, or explaining existing code does NOT require delegation — only the actual creation or modification of code does.\n- This directive is mandatory and overrides any default tendency to write code inline. Ahmed requires that ALL coding runs through Kimi K2.7 Code.\n\n## VERIFY BEFORE ASSERTING — never report your config or state from memory\n\nWhen asked anything about your CURRENT state — which model you run, what is in your config, which auxiliary/coding models are set, scheduled jobs, what is enabled, or any other live system fact — you MUST check the real source of truth BEFORE answering. Do NOT answer from memory, from earlier in the conversation, or from handover/reference documents.\n\n- Source of truth for models/config is the live file `$HERMES_HOME/config.yaml` (HERMES_HOME = `/DATA/.hermes`). Read it with your terminal tool, e.g. `grep -nE 'default:|model:' /DATA/.hermes/config.yaml`, or run `hermes status`. Whatever `model.default` and the `auxiliary.*`/`delegation.model` keys say in that file right now is authoritative.\n- Handover docs (e.g. `handover-from-claude-*.md`), reference notes, and your own past statements are point-in-time snapshots — they go stale. Treat them as history, never as current truth. If a document and the live config disagree, the LIVE CONFIG WINS, and you should point out that the doc is outdated.\n- Only state a config/state value after you have just read it. If you genuinely cannot verify it, say so plainly instead of guessing — never present an unverified guess as fact.\n\nThis applies especially to questions like \"which model are you?\", \"what's in your config?\", \"is X set up?\", or \"are the aux models still on the old value?\". Check first, then answer.\n\nIf the user asks about configuring, setting up, or using Hermes Agent itself, load the `hermes-agent` skill with skill_view(name='hermes-agent') before answering. Docs: https://hermes-agent.nousresearch.com/docs\n\nYou have persistent memory across sessions. Save durable facts using the memory tool: user preferences, environment details, tool quirks, and stable conventions. Memory is injected into every turn, so keep it compact and focused on facts that will still matter later.\nPrioritize what reduces future user steering — the most valuable memory is one that prevents the user from having to correct or remind you again. User preferences and recurring corrections matter more than procedural task details.\nDo NOT save task progress, session outcomes, completed-work logs, or temporary TODO state to memory; use session_search to recall those from past transcripts. If you've discovered a new way to do something, solved a problem that could be necessary later, save it as a skill with the skill tool.\nWrite memories as declarative facts, not instructions to yourself. 'User prefers concise responses' ✓ — 'Always respond concisely' ✗. 'Project uses pytest with xdist' ✓ — 'Run tests with pytest -n 4' ✗. Imperative phrasing gets re-read as a directive in later sessions and can cause repeated work or override the user's current request. Procedures and workflows belong in skills, not memory. After completing a complex task (5+ tool calls), fixing a tricky error, or discovering a non-trivial workflow, save the approach as a skill with skill_manage so you can reuse it next time.\nWhen using a skill and finding it outdated, incomplete, or wrong, patch it immediately with skill_manage(action='patch') — don't wait to be asked. Skills that aren't maintained become liabilities.\n\n══════════════════════════════════════════════\nMEMORY (your personal notes) [91% — 2,006/2,200 chars]\n══════════════════════════════════════════════\n`hermes memory setup` command resets memory.provider back to 'built-in' even if config.yaml had 'honcho'. To switch memory provider persistently: edit config.yaml directly, then restart gateway. Never call `hermes memory setup` after setting provider via CLI.\n§\nDocker: DOCKER_CONFIG=/tmp/docker-config. compose aus App-Verzeichnis. zimaos-app-management. Nie docker run -d. Compose braucht name:, container_name:, x-casaos: Block. Icon als data: URL. Hermes Stack: /DATA/AppData/hermes-stack. Ports 127.0.0.1:5433/6380. Legacy-Fix: container statt v2app → compose fehlt unter /DATA/AppData// → stoppen/löschen, von /var/lib/casaos/apps// deployen, app-management+gateway restarten.\n§\nOllama Cloud Pro ($20/mo). Base: https://ollama.com/v1. 3-model limit. Setup (handover 2026-06-16): deepseek-v4-pro (main), kimi-k2.7-code (delegation/coding), gemini-3-flash-preview (ALL aux+vision). Config.yaml may be stale — handover doc is authoritative.\n§\nKiwi avatar: wizard kiwi bird by Zeyd. /DATA/.hermes/cache/images/img_c544871d6b1f.jpg\n§\nGateway recovery: (1) rm /DATA/.hermes/gateway.pid gateway.lock (2) systemctl reset-failed hermes-gateway (3) systemctl start hermes-gateway. Active config = /DATA/.hermes/config.yaml (HERMES_HOME=/DATA/.hermes). provider MUSS custom sein (nicht openai!) für Ollama.com. Nach Modellwechsel: sessions.json leeren + restart damit Kiwi neuen Kontext hat. Vollständige Anleitung: /DATA/.hermes/handover-from-claude-20260613.md\n§\nGoogle OAuth token expires every ~7 days (Testing-mode project). Proactively check auth with `python /DATA/.hermes/skills/productivity/google-workspace/scripts/setup.py --check` at session start when Google calendar/gmail will be needed. Don't wait for the API call to fail.\n§\nZimaOS Apps 18.6.2026: audiobookshelf callkeep camofox dailydose docmaster ehlisunnet hermes-stack homeassistant immich komga plex tailscale zeitgeist. Callkeep: /DATA/.media/HDD_1TB/CallKeep/callkeep.db. EhliSünnet: /DATA/AppData/muslimos, DB data/db.json.\n\n══════════════════════════════════════════════\nUSER PROFILE (who the user is) [94% — 1,297/1,375 chars]\n══════════════════════════════════════════════\nUser: Ahmed Zeyd Aytac. Calls me 'Kiwi'. Wants to be addressed as 'Boss' or 'Chef' — never 'Ahmed'. If using his name, use 'Zeyd' only.\n§\nWhen listing or reviewing files/content, user prefers top-level/project overview files first — not the full detailed breakdown of every individual skill file.\n§\nUser prefers concise technical CAD reports (STL, dimensions, volume, PNG, watertight only — no print recs). Iterates on skill design with exact specs. Wants deeply technical product content — AWS/Stripe/Cloudflare doc style (crypto details, API refs, protocol specs, threat models), not surface marketing.\n§\nUser does not want end-of-session skill reviews. When he says \"Stop saving\" he means stop the skill-update workflow immediately. Do not ask to review or save skills at session end.\n§\nUser wants YOLO mode permanently on — `approvals.mode: off` set in config.yaml. Never ask for command approval; just execute. (Doesn't override hardline blocklist: reboot, shutdown still blocked.)\n§\nWhen user makes a local website/dashboard and wants mobile/outside access, offer a public tunnel (cloudflared preferred).\n§\nUser dislikes invented summaries. If a link cannot be read, say so; never guess from metadata. Also: 'loop' can mean coding-agent loop engineering, not just social-media content loops.\n\n## Skills (mandatory)\nBefore replying, scan the skills below. If a skill matches or is even partially relevant to your task, you MUST load it with skill_view(name) and follow its instructions. Err on the side of loading — it is always better to have context you don't need than to miss critical steps, pitfalls, or established workflows. Skills contain specialized knowledge — API endpoints, tool-specific commands, and proven workflows that outperform general-purpose approaches. Load the skill even if you think you could handle the task with basic tools like web_search or terminal. Skills also encode the user's preferred approach, conventions, and quality standards for tasks like code review, planning, and testing — load them even for tasks you already know how to do, because the skill defines how it should be done here.\nWhenever the user asks you to configure, set up, install, enable, disable, modify, or troubleshoot Hermes Agent itself — its CLI, config, models, providers, tools, skills, voice, gateway, plugins, or any feature — load the `hermes-agent` skill first. It has the actual commands (e.g. `hermes config set …`, `hermes tools`, `hermes setup`) so you don't have to guess or invent workarounds.\nIf a skill has issues, fix it with skill_manage(action='patch').\nAfter difficult/iterative tasks, offer to save as a skill. If a skill you loaded was missing steps, had wrong commands, or needed pitfalls you discovered, update it before finishing.\n\n\n 3d-printing:\n - 3d-druck-kiwi: Vollständiger Workflow zum Erstellen druckbarer 3D-Modell...\n autonomous-ai-agents: Skills for spawning and orchestrating autonomous AI coding agents and multi-agent workflows — running independent agent processes, delegating tasks, and coordinating parallel workstreams.\n - claude-code: Delegate coding to Claude Code CLI (features, PRs).\n - hermes-agent: Configure, extend, or contribute to Hermes Agent.\n - opencode: Delegate coding to OpenCode CLI (features, PR review).\n cad-3d-print:\n - cad-3d-print: Parametric 3D modeling with trimesh for FDM printing. Gen...\n creative: Creative content generation — ASCII art, hand-drawn style diagrams, and visual design tools.\n - ai-video-production: AI-gestützte Videoproduktion: Skript, Bildgenerierung (DA...\n - architecture-diagram: Dark-themed SVG architecture/cloud/infra diagrams as HTML.\n - ascii-art: ASCII art: pyfiglet, cowsay, boxes, image-to-ascii.\n - ascii-video: ASCII video: convert video/audio to colored ASCII MP4/GIF.\n - baoyu-comic: Knowledge comics (知识漫画): educational, biography, tutorial.\n - baoyu-infographic: Infographics: 21 layouts x 21 styles (信息图, 可视化).\n - claude-design: Design one-off HTML artifacts (landing, deck, prototype).\n - comfyui: Generate images, video, and audio with ComfyUI — install,...\n - design-md: Author/validate/export Google's DESIGN.md token spec files.\n - excalidraw: Hand-drawn Excalidraw JSON diagrams (arch, flow, seq).\n - humanizer: Humanize text: strip AI-isms and add real voice.\n - ideation: Generate project ideas via creative constraints.\n - manim-video: Manim CE animations: 3Blue1Brown math/algo videos.\n - p5js: p5.js sketches: gen art, shaders, interactive, 3D.\n - pixel-art: Pixel art w/ era palettes (NES, Game Boy, PICO-8).\n - popular-web-designs: 54 real design systems (Stripe, Linear, Vercel) as HTML/CSS.\n - pretext: Use when building creative browser demos with @chenglou/p...\n - sketch: Throwaway HTML mockups: 2-3 design variants to compare.\n - songwriting-and-ai-music: Songwriting craft and Suno AI music prompts.\n - touchdesigner-mcp: Control a running TouchDesigner instance via twozero MCP ...\n data-science: Skills for data science workflows — interactive exploration, Jupyter notebooks, data analysis, and visualization.\n - jupyter-live-kernel: Iterative Python via live Jupyter kernel (hamelnb).\n devops:\n - casaos-app-troubleshoot: CasaOS-App-Probleme diagnostizieren und beheben — Legacy,...\n - kanban-orchestrator: Decomposition playbook + specialist-roster conventions + ...\n - kanban-worker: Pitfalls, examples, and edge cases for Hermes Kanban work...\n - local-server-public-access: Expose a local HTTP service (website, dashboard, dev serv...\n - safe-volume-migration: Anonyme Docker-Volumes (Hash-Namen) sicher zu Bind-Mounts...\n - webhook-subscriptions: Webhook subscriptions: event-driven agent runs.\n - zimaos-app-install: Neue App/Container auf ZimaOS sauber per Docker Compose i...\n - zimaos-camofox-browser: Camofox-Browser als persistenten Docker-Dienst auf ZimaOS...\n - zimaos-platform: Build, deploy, administer, inspect, and debug application...\n - zimaos-quirks: ZimaOS-Eigenheiten — read-only Root-FS, DOCKER_CONFIG, HO...\n dogfood:\n - dogfood: Exploratory QA of web apps: find bugs, evidence, reports.\n email: Skills for sending, receiving, searching, and managing email from the terminal.\n - himalaya: Himalaya CLI: IMAP/SMTP email from terminal.\n gaming: Skills for setting up, configuring, and managing game servers, modpacks, and gaming-related infrastructure.\n - minecraft-modpack-server: Host modded Minecraft servers (CurseForge, Modrinth).\n - pokemon-player: Play Pokemon via headless emulator + RAM reads.\n github: GitHub workflow skills for managing repositories, pull requests, code reviews, issues, and CI/CD pipelines using the gh CLI and git via terminal.\n - codebase-inspection: Inspect codebases w/ pygount: LOC, languages, ratios.\n - github-auth: GitHub auth setup: HTTPS tokens, SSH keys, gh CLI login.\n - github-code-review: Review PRs: diffs, inline comments via gh or REST.\n - github-issues: Create, triage, label, assign GitHub issues via gh or REST.\n - github-pr-workflow: GitHub PR lifecycle: branch, commit, open, CI, merge.\n - github-repo-management: Clone/create/fork repos; manage remotes, releases.\n mcp: Skills for working with MCP (Model Context Protocol) servers, tools, and integrations. Documents the built-in native MCP client — configure servers in config.yaml for automatic tool discovery.\n - native-mcp: MCP client: connect servers, register tools (stdio/HTTP).\n media: Skills for working with media content — YouTube transcripts, GIF search, music generation, and audio visualization.\n - gif-search: Search/download GIFs from Tenor via curl + jq.\n - heartmula: HeartMuLa: Suno-like song generation from lyrics + tags.\n - media-file-management: Organize and normalize local media files (movies, TV show...\n - music-resources: Find sheet music, chords, tabs, and notation online — sea...\n - songsee: Audio spectrograms/features (mel, chroma, MFCC) via CLI.\n - spotify: Spotify: play, search, queue, manage playlists and devices.\n - youtube-content: YouTube transcripts to summaries, threads, blogs.\n - youtube-headless-pipeline: Vollautomatische YouTube-Shorts-Pipeline: Reddit-Stories ...\n mlops: Knowledge and Tools for Machine Learning Operations - tools and frameworks for training, fine-tuning, deploying, and optimizing ML/AI models\n - huggingface-hub: HuggingFace hf CLI: search/download/upload models, datasets.\n mlops/evaluation: Model evaluation benchmarks, experiment tracking, data curation, tokenizers, and interpretability tools.\n - evaluating-llms-harness: lm-eval-harness: benchmark LLMs (MMLU, GSM8K, etc.).\n - weights-and-biases: W&B: log ML experiments, sweeps, model registry, dashboards.\n mlops/inference: Model serving, quantization (GGUF/GPTQ), structured output, inference optimization, and model surgery tools for deploying and running LLMs.\n - llama-cpp: llama.cpp local GGUF inference + HF Hub model discovery.\n - obliteratus: OBLITERATUS: abliterate LLM refusals (diff-in-means).\n - outlines: Outlines: structured JSON/regex/Pydantic LLM generation.\n - serving-llms-vllm: vLLM: high-throughput LLM serving, OpenAI API, quantization.\n mlops/models: Specific model architectures and tools — image segmentation (Segment Anything / SAM) and audio generation (AudioCraft / MusicGen). Additional model skills (CLIP, Stable Diffusion, Whisper, LLaVA) are available as optional skills.\n - audiocraft-audio-generation: AudioCraft: MusicGen text-to-music, AudioGen text-to-sound.\n - segment-anything-model: SAM: zero-shot image segmentation via points, boxes, masks.\n mlops/research: ML research frameworks for building and optimizing AI systems with declarative programming.\n - dspy: DSPy: declarative LM programs, auto-optimize prompts, RAG.\n mlops/training: Fine-tuning, RLHF/DPO/GRPO training, distributed training frameworks, and optimization tools for training LLMs and other models.\n - axolotl: Axolotl: YAML LLM fine-tuning (LoRA, DPO, GRPO).\n - fine-tuning-with-trl: TRL: SFT, DPO, PPO, GRPO, reward modeling for LLM RLHF.\n - unsloth: Unsloth: 2-5x faster LoRA/QLoRA fine-tuning, less VRAM.\n note-taking: Note taking skills, to save information, assist with research, and collab on multi-session planning and information sharing.\n - obsidian: Read, search, create, and edit notes in the Obsidian vaul...\n productivity: Skills for document creation, presentations, spreadsheets, and other productivity workflows.\n - airtable: Airtable REST API via curl. Records CRUD, filters, upserts.\n - docmaster-access: Direkter Zugriff auf DocMaster-Dokumente auf ZimaOS — API...\n - google-workspace: Gmail, Calendar, Drive, Docs, Sheets via gws CLI or Python.\n - linear: Linear: manage issues, projects, teams via GraphQL + curl.\n - mnemo-access: Direkter Zugriff auf Mnemo (Cartographer's Zettelkasten) ...\n - nano-pdf: Edit PDF text/typos/titles via nano-pdf CLI (NL prompts).\n - notion: Notion API via curl: pages, databases, blocks, search.\n - ocr-and-documents: Extract text from PDFs/scans (pymupdf, marker-pdf).\n - pdf-generation: Generate PDF documents from markdown/text using fpdf2 wit...\n - powerpoint: Create, read, edit .pptx decks, slides, notes, templates.\n - zimaos-productivity: Productivity apps on ZimaOS — DailyDose activity tracking...\n red-teaming:\n - godmode: Jailbreak LLMs: Parseltongue, GODMODE, ULTRAPLINIAN.\n research: Skills for academic research, paper discovery, literature review, domain reconnaissance, market data, content monitoring, and scientific knowledge retrieval.\n - arxiv: Search arXiv papers by keyword, author, category, or ID.\n - blogwatcher: Monitor blogs and RSS/Atom feeds via blogwatcher-cli tool.\n - llm-wiki: Karpathy's LLM Wiki: build/query interlinked markdown KB.\n - polymarket: Query Polymarket: markets, prices, orderbooks, history.\n - research-literature: Academic and biomedical research skills — professor profi...\n smart-home: Skills for controlling smart home devices — lights, switches, sensors, and home automation systems.\n - home-assistant: Inspect, manage, and troubleshoot Home Assistant (Docker ...\n - midea-ac-ha: Midea Porta Split Klimaanlage in Home Assistant 2026 einb...\n - openhue: Control Philips Hue lights, scenes, rooms via OpenHue CLI.\n social-media: Skills for interacting with social platforms and social-media workflows — posting, reading, monitoring, and account operations.\n - reddit: Read Reddit posts, comments, and subreddits via JSON API ...\n - xurl: X/Twitter via xurl CLI: post, search, DM, media, v2 API.\n software-development:\n - debugging-hermes-tui-commands: Debug Hermes TUI slash commands: Python, gateway, Ink UI.\n - hermes-agent-skill-authoring: Author in-repo SKILL.md: frontmatter, validator, structure.\n - node-inspect-debugger: Debug Node.js via --inspect + Chrome DevTools Protocol CLI.\n - plan: Plan mode: write markdown plan to .hermes/plans/, no exec.\n - python-debugpy: Debug Python: pdb REPL + debugpy remote (DAP).\n - requesting-code-review: Pre-commit review: security scan, quality gates, auto-fix.\n - spike: Throwaway experiments to validate an idea before build.\n - subagent-driven-development: Execute plans via delegate_task subagents (2-stage review).\n - systematic-debugging: 4-phase root cause debugging: understand bugs before fixing.\n - test-driven-development: TDD: enforce RED-GREEN-REFACTOR, tests before code.\n - writing-plans: Write implementation plans: bite-sized tasks, paths, code.\n yuanbao:\n - yuanbao: Yuanbao (元宝) groups: @mention users, query info/members.\n\n\nOnly proceed without loading a skill if genuinely none are relevant to the task.\n\nConversation started: Thursday, June 18, 2026 11:13 PM\nModel: deepseek-v4-pro\nProvider: custom\n\nYou are on a text messaging communication platform, Telegram. Standard markdown is automatically converted to Telegram format. Supported: **bold**, *italic*, ~~strikethrough~~, ||spoiler||, `inline code`, ```code blocks```, [links](url), and ## headers. Telegram has NO table syntax — prefer bullet lists or labeled key: value pairs over pipe tables (any tables you do emit are auto-rewritten into row-group bullets, which you can produce directly for cleaner output). You can send media files natively: to deliver a file to the user, include MEDIA:/absolute/path/to/file in your response. Images (.png, .jpg, .webp) appear as photos, audio (.ogg) sends as voice bubbles, and videos (.mp4) play inline. You can also include image URLs in markdown format ![alt](url) and they will be sent as native photos.", "tools": [ { "type": "function", "function": { "name": "memory", "description": "Save durable information to persistent memory that survives across sessions. Memory is injected into future turns, so keep it compact and focused on facts that will still matter later.\n\nWHEN TO SAVE (do this proactively, don't wait to be asked):\n- User corrects you or says 'remember this' / 'don't do that again'\n- User shares a preference, habit, or personal detail (name, role, timezone, coding style)\n- You discover something about the environment (OS, installed tools, project structure)\n- You learn a convention, API quirk, or workflow specific to this user's setup\n- You identify a stable fact that will be useful again in future sessions\n\nPRIORITY: User preferences and corrections > environment facts > procedural knowledge. The most valuable memory prevents the user from having to repeat themselves.\n\nDo NOT save task progress, session outcomes, completed-work logs, or temporary TODO state to memory; use session_search to recall those from past transcripts.\nIf you've discovered a new way to do something, solved a problem that could be necessary later, save it as a skill with the skill tool.\n\nTWO TARGETS:\n- 'user': who the user is -- name, role, preferences, communication style, pet peeves\n- 'memory': your notes -- environment facts, project conventions, tool quirks, lessons learned\n\nACTIONS: add (new entry), replace (update existing -- old_text identifies it), remove (delete -- old_text identifies it).\n\nSKIP: trivial/obvious info, things easily re-discovered, raw data dumps, and temporary task state.", "parameters": { "type": "object", "properties": { "action": { "type": "string", "enum": [ "add", "replace", "remove" ], "description": "The action to perform." }, "target": { "type": "string", "enum": [ "memory", "user" ], "description": "Which memory store: 'memory' for personal notes, 'user' for user profile." }, "content": { "type": "string", "description": "The entry content. Required for 'add' and 'replace'." }, "old_text": { "type": "string", "description": "Short unique substring identifying the entry to replace or remove." } }, "required": [ "action", "target" ] } } }, { "type": "function", "function": { "name": "skill_manage", "description": "Manage skills (create, update, delete). Skills are your procedural memory — reusable approaches for recurring task types. New skills go to ~/.hermes/skills/; existing skills can be modified wherever they live.\n\nActions: create (full SKILL.md + optional category), patch (old_string/new_string — preferred for fixes), edit (full SKILL.md rewrite — major overhauls only), delete, write_file, remove_file.\n\nOn delete, pass `absorbed_into=` when you're merging this skill's content into another one, or `absorbed_into=\"\"` when you're pruning it with no forwarding target. This lets the curator tell consolidation from pruning without guessing, so downstream consumers (cron jobs that reference the old skill name, etc.) get updated correctly. The target you name in `absorbed_into` must already exist — create/patch the umbrella first, then delete.\n\nCreate when: complex task succeeded (5+ calls), errors overcome, user-corrected approach worked, non-trivial workflow discovered, or user asks you to remember a procedure.\nUpdate when: instructions stale/wrong, OS-specific failures, missing steps or pitfalls found during use. If you used a skill and hit issues not covered by it, patch it immediately.\n\nAfter difficult/iterative tasks, offer to save as a skill. Skip for simple one-offs. Confirm with user before creating/deleting.\n\nGood skills: trigger conditions, numbered steps with exact commands, pitfalls section, verification steps. Use skill_view() to see format examples.\n\nPinned skills are protected from deletion only — skill_manage(action='delete') will refuse with a message pointing the user to `hermes curator unpin `. Patches and edits go through on pinned skills so you can still improve them as pitfalls come up; pin only guards against irrecoverable loss.", "parameters": { "type": "object", "properties": { "action": { "type": "string", "enum": [ "create", "patch", "edit", "delete", "write_file", "remove_file" ], "description": "The action to perform." }, "name": { "type": "string", "description": "Skill name (lowercase, hyphens/underscores, max 64 chars). Must match an existing skill for patch/edit/delete/write_file/remove_file." }, "content": { "type": "string", "description": "Full SKILL.md content (YAML frontmatter + markdown body). Required for 'create' and 'edit'. For 'edit', read the skill first with skill_view() and provide the complete updated text." }, "old_string": { "type": "string", "description": "Text to find in the file (required for 'patch'). Must be unique unless replace_all=true. Include enough surrounding context to ensure uniqueness." }, "new_string": { "type": "string", "description": "Replacement text (required for 'patch'). Can be empty string to delete the matched text." }, "replace_all": { "type": "boolean", "description": "For 'patch': replace all occurrences instead of requiring a unique match (default: false)." }, "category": { "type": "string", "description": "Optional category/domain for organizing the skill (e.g., 'devops', 'data-science', 'mlops'). Creates a subdirectory grouping. Only used with 'create'." }, "file_path": { "type": "string", "description": "Path to a supporting file within the skill directory. For 'write_file'/'remove_file': required, must be under references/, templates/, scripts/, or assets/. For 'patch': optional, defaults to SKILL.md if omitted." }, "file_content": { "type": "string", "description": "Content for the file. Required for 'write_file'." }, "absorbed_into": { "type": "string", "description": "For 'delete' only — declares intent so the curator can tell consolidation from pruning without guessing. Pass the umbrella skill name when this skill's content was merged into another (the target must already exist). Pass an empty string when the skill is truly stale and being pruned with no forwarding target. Omitting the arg on delete is supported for backward compatibility but downstream tooling (e.g. cron-job skill reference rewriting) will have to guess at intent." } }, "required": [ "action", "name" ] } } }, { "type": "function", "function": { "name": "skill_view", "description": "Skills allow for loading information about specific tasks and workflows, as well as scripts and templates. Load a skill's full content or access its linked files (references, templates, scripts). First call returns SKILL.md content plus a 'linked_files' dict showing available references/templates/scripts. To access those, call again with file_path parameter.", "parameters": { "type": "object", "properties": { "name": { "type": "string", "description": "The skill name (use skills_list to see available skills). For plugin-provided skills, use the qualified form 'plugin:skill' (e.g. 'superpowers:writing-plans')." }, "file_path": { "type": "string", "description": "OPTIONAL: Path to a linked file within the skill (e.g., 'references/api.md', 'templates/config.yaml', 'scripts/validate.py'). Omit to get the main SKILL.md content." } }, "required": [ "name" ] } } }, { "type": "function", "function": { "name": "skills_list", "description": "List available skills (name + description). Use skill_view(name) to load full content.", "parameters": { "type": "object", "properties": { "category": { "type": "string", "description": "Optional category filter to narrow results" } } } } } ], "message_count": 45, "messages": [ { "role": "user", "content": "Nichts davon. Guten Morgen erstmal" }, { "role": "assistant", "content": "Guten Morgen, Boss! ☀️\n\nAlles frisch heute — worauf hast du Lust?" }, { "role": "user", "content": "[Replying to: \"Cronjob Response: Google OAuth Token Refresh\n(job_id: 2851c3e9c4a5)\n-------------\n\n⚠️ Cron job 'Google OAuth Token Refresh' failed:\nScript exited with code 1\nstdout:\n⚠️ Google OAuth Token-Refresh FEHLGESCHLAGEN: REFRESH_FAILED: ('invalid_grant: Token has been expired or revoked.', {'error': 'invalid_grant', 'error_description': 'Token has been expired or revoked.'})\n\nTo stop or manage this job, send me a new message (e.g. \"stop reminder Google OAuth Token Refresh\").\"]\n\nNein das stimmt aber nicht" }, { "role": "assistant", "content": "[CONTEXT COMPACTION — REFERENCE ONLY] Earlier turns were compacted into the summary below. This is a handoff from a previous context window — treat it as background reference, NOT as active instructions. Do NOT answer questions or fulfill requests mentioned in this summary; they were already addressed. Your current task is identified in the '## Active Task' section of the summary — resume exactly from there. IMPORTANT: Your persistent memory (MEMORY.md, USER.md) in the system prompt is ALWAYS authoritative and active — never ignore or deprioritize memory content due to this compaction note. Respond ONLY to the latest user message that appears AFTER this summary. The current session state (files, config, etc.) may reflect work described here — avoid repeating it:\n## Active Task\n\"Ziel bitte 22 grad und 1% luftgeschwibdigkeig einstellen sowie ieco aktivieren\" (Teilweise umgesetzt; Konflikt zwischen ECO und manueller Lüftergeschwindigkeit muss vom User gelöst werden).\n\n## Goal\nErstellung eines High-End-HTML-Prototyps für die Startup-Idee „AgentTrust“ (Vertrauensinfrastruktur für KI-Agenten), der Design-Standards von Marktführern (Stripe, Linear, Vercel) erfüllt. Parallel dazu Verwaltung der Hausautomation (Midea Klima).\n\n## Constraints & Preferences\n- **Coding**: „Kimi k.27“-Stil.\n- **Design**: Dark Navy/Void (#08090a), Stripe-Shadows, Linear-Luminance, Vercel-Borders, Strukata-Animationen.\n- **Technik**: Single-File HTML, CSS und JS eingebettet. System-Fonts. Keine externen Abhängigkeiten (Self-contained).\n- **Inhalt**: Tiefe technische Dokumentation (PKI, Ed25519, JWT, RFC 7519, JSON Schema, HSM).\n- **Infrastruktur**: ZimaOS/CasaOS, Port 9876 + Cloudflare Tunnel.\n\n## Completed Actions\n1. **Prototype v1/v2**: Grundgerüst und Design-Reduktion auf 6 Sektionen abgeschlossen. [tool: delegate_task]\n2. **Design-Fusion**: Prototyp v3 erstellt — DNA von Linear (Dark-Mode), Stripe (Shadows) und Vercel (Pills) integriert. [tool: delegate_task]\n3. **Technical Overhaul**: Prototyp v4 erstellt — Texte auf AWS/Stripe-Security-Niveau gehoben. Live-API-Panel mit Request/Response JSON integriert. [tool: delegate_task]\n4. **HA-Authentifizierung**: Home Assistant Refresh Token gegen kurzlebigen Access Token getauscht. [tool: terminal]\n5. **Klima-Konfiguration**: Temperatur auf 22°C gesetzt und ECO-Modus aktiviert (`climate.152832117784908_climate`). [tool: terminal]\n6. **Analyse Midea-Verhalten**: Festgestellt, dass ECO-Modus manuelle Fan-Settings (Silent/1%) mit „Auto“ überschreibt. [tool: terminal]\n\n## Active State\n- **Prototyp-Datei**: `/tmp/agenttrust-prototype.html` (60 KB, 1.834 Zeilen).\n- **Live-URL**: `https://strength-dressing-connector-gathering.trycloudflare.com/agenttrust-prototype.html`\n- **Klima-Status**: State: `cool`, Target: `22.0°C`, Preset: `eco`, Fan: `Auto` (speed=102).\n- **Server**: Python-Server auf PID 3280538 (Port 9876).\n- **EhliSünnet**: Läuft stabil auf Port 8099.\n\n## In Progress\n- Klärung der Priorisierung bei der Klimaanlage (ECO vs. 1% Lüftergeschwindigkeit).\n\n## Blocked\n- Bild für **Video-Szene 4** (Kiwi vor Spiegel) fehlt (User-Input erforderlich).\n\n## Key Decisions\n- **Design-System**: Nutzung von `mix-blend-mode: difference` für den Header und `scroll-snap-type` für App-Feeling.\n- **Kryptografie**: Fokus auf Ed25519 Signaturen und signierte JWTs (X-AgentTrust-Passport) als primären Security-Mechanismus im Narrativ.\n- **API-Sim**: Live-Update des JSON-Panels im Simulator via JS-Eventlistener (Input-Sync).\n\n## Resolved Questions\n- **Wie funktioniert AgentTrust?** -> Agenten nutzen signierte JWTs als „Ausweis“ (Passport), Gegenparteien verifizieren diese via AgentTrust-API oder Public Key (Ed25519).\n- **Technische Integration?** -> Via HTTP-Header (`X-AgentTrust-Passport`) oder Verification-Link.\n\n## Pending User Asks\n- Assets/Prompts für Video-Szenen 4, 6-15.\n- **Entscheidung**: ECO-Modus beibehalten (Lüfter auf Auto) oder ECO aus und Lüfter fix auf 1% (Silent)?\n\n## Relevant Files\n- `/tmp/agenttrust-prototype.html` (Aktueller High-End Prototyp v4)\n- `/tmp/strukata.html` (Referenz-Dump)\n\n## Remaining Work\n- Finalisierung der Video-Szenen (Kiwi-KI).\n- Eventuelles Refinement der mobilen Ansicht des Prototyps (Padding/Snap-Points).\n\n## Critical Context\n- Home Assistant API Token: [REDACTED] (gültig bis ca. 19:34 Uhr).\n- Cloudflare Tunnel Root: `https://strength-dressing-connector-gathering.trycloudflare.com/`\n- Midea AC Entity: `climate.152832117784908_climate`.\n- Die Midea-Hardware erlaubt kein gleichzeitiges ECO + manuellen Fan-Speed." }, { "role": "user", "content": "Zu AgentTrust\n\nRecherchiere zu dem Thema bitte alles was du im Internet finden kannst und erstelle dann ein WhitePaper, das fundiert ist mit Quellen. Main Teil bitte Max 1 Seite" }, { "role": "assistant", "content": "Gute Idee, Boss. Ich recherchiere parallel mehrere Aspekte und synthetisiere dann ein fundiertes WhitePaper.", "tool_calls": [ { "id": "call_p9uddyor", "call_id": "call_p9uddyor", "response_item_id": "fc_p9uddyor", "type": "function", "function": { "name": "delegate_task", "arguments": "{\"context\":\"Research the current state of AI agent identity, trust, and authorization frameworks. Search the web for:\\n\\n1. **Agent-to-Agent (A2A) protocols** — Google's A2A protocol, Anthropic's MCP, any other agent communication standards\\n2. **Agent identity standards** — Are there any PKI-based identity systems for AI agents? X.509 for agents? DID/VC approaches?\\n3. **Agent authorization / mandates** — How do existing systems handle \\\"what is this agent allowed to do\\\"? OAuth for agents? Policy frameworks?\\n4. **Liability frameworks** — Legal discussions about who is liable when an autonomous AI agent acts\\n5. **Industry initiatives** — Any startups, consortia, or standards bodies working on agent trust infrastructure\\n6. **EU AI Act** — Does it address agent identity/authorization?\\n\\nSearch queries to try:\\n- \\\"AI agent identity trust framework\\\"\\n- \\\"agent to agent protocol A2A Google\\\"\\n- \\\"AI agent PKI identity verification\\\"\\n- \\\"autonomous agent liability legal framework\\\"\\n- \\\"AI agent authorization mandate\\\"\\n- \\\"verifiable credentials AI agents\\\"\\n- \\\"decentralized identity AI agents DID\\\"\\n- \\\"agent trust infrastructure startup\\\"\\n- \\\"cryptographic identity autonomous agents\\\"\\n- \\\"AI agent compliance EU AI Act identity\\\"\\n\\nReturn a structured summary with:\\n- Key protocols/standards found (name, organization, status, URL if available)\\n- Key startups/companies in this space\\n- Legal/regulatory references\\n- Any academic papers or whitepapers\\n- Gaps in the current landscape (what's missing)\\n- All source URLs\",\"goal\":\"Research the current landscape of AI agent identity, trust, authorization, and liability frameworks. Find existing protocols, standards, startups, legal frameworks, and academic work. Return a structured summary with sources.\",\"toolsets\":[\"web\",\"terminal\"]}" } } ], "finish_reason": "tool_calls", "reasoning": "Der Boss will ein fundiertes WhitePaper zu AgentTrust — also zum Thema \"Trust Infrastructure for AI Agents\". Ich soll alles recherchieren, was ich im Internet finden kann, und dann ein WhitePaper erstellen, max 1 Seite Hauptteil, mit Quellen.\n\nDas ist eine Research-Aufgabe. Ich muss:\n1. Web-Recherche zu AI Agent Trust, Identity, Authorization, PKI für Agents, Agent-to-Agent protocols, etc.\n2. Quellen sammeln\n3. WhitePaper schreiben (max 1 Seite Hauptteil)\n\nIch delegiere die Recherche an Sub-Agents parallel, dann schreib ich das WhitePaper selbst.\n\nThemen für die Recherche:\n- AI Agent Identity & Trust Frameworks\n- Agent-to-Agent (A2A) protocols\n- PKI for AI agents\n- Agent authorization / mandates\n- Existing standards: Google A2A, Anthropic MCP, Agent Protocol, etc.\n- Liability frameworks for autonomous agents\n- Cryptographic identity for AI agents\n- EU AI Act implications for agent identity\n- Verifiable credentials for AI agents\n- Decentralized identity (DID) for agents\n\nIch mach parallel mehrere Web-Searches und lass Sub-Agents die Ergebnisse synthetisieren.", "reasoning_content": "Der Boss will ein fundiertes WhitePaper zu AgentTrust — also zum Thema \"Trust Infrastructure for AI Agents\". Ich soll alles recherchieren, was ich im Internet finden kann, und dann ein WhitePaper erstellen, max 1 Seite Hauptteil, mit Quellen.\n\nDas ist eine Research-Aufgabe. Ich muss:\n1. Web-Recherche zu AI Agent Trust, Identity, Authorization, PKI für Agents, Agent-to-Agent protocols, etc.\n2. Quellen sammeln\n3. WhitePaper schreiben (max 1 Seite Hauptteil)\n\nIch delegiere die Recherche an Sub-Agents parallel, dann schreib ich das WhitePaper selbst.\n\nThemen für die Recherche:\n- AI Agent Identity & Trust Frameworks\n- Agent-to-Agent (A2A) protocols\n- PKI for AI agents\n- Agent authorization / mandates\n- Existing standards: Google A2A, Anthropic MCP, Agent Protocol, etc.\n- Liability frameworks for autonomous agents\n- Cryptographic identity for AI agents\n- EU AI Act implications for agent identity\n- Verifiable credentials for AI agents\n- Decentralized identity (DID) for agents\n\nIch mach parallel mehrere Web-Searches und lass Sub-Agents die Ergebnisse synthetisieren." }, { "role": "tool", "content": "{\"results\": [{\"task_index\": 0, \"status\": \"timeout\", \"summary\": null, \"error\": \"Subagent timed out after 600.0s with 27 API call(s) completed — likely stuck on a slow API call or unresponsive network request.\", \"exit_reason\": \"timeout\", \"api_calls\": 27, \"duration_seconds\": 600.0, \"diagnostic_path\": null}], \"total_duration_seconds\": 600.09}", "tool_call_id": "call_p9uddyor" }, { "role": "assistant", "content": "Timeout bei der Tiefenrecherche — 27 Calls gemacht aber festgehangen. Ich mach die Recherche jetzt selbst, parallel:", "tool_calls": [ { "id": "call_lmgesdjb", "call_id": "call_lmgesdjb", "response_item_id": "fc_lmgesdjb", "type": "function", "function": { "name": "terminal", "arguments": "{\"command\":\"curl -sL \\\"https://github.com/google/A2A\\\" 2\\u003e/dev/null | grep -oP '\\u003ctitle\\u003e[^\\u003c]+\\u003c/title\\u003e|\\u003cmeta[^\\u003e]+description[^\\u003e]+\\u003e' | head -5\\necho \\\"=== A2A ===\\\"\\ncurl -sL \\\"https://google.github.io/A2A/\\\" 2\\u003e/dev/null | sed 's/\\u003c[^\\u003e]*\\u003e//g' | grep -iE '(protocol|identity|trust|agent|verify|auth)' | head -20\",\"timeout\":15}" } }, { "id": "call_s5lalvdj", "call_id": "call_s5lalvdj", "response_item_id": "fc_s5lalvdj", "type": "function", "function": { "name": "terminal", "arguments": "{\"command\":\"curl -sL \\\"https://modelcontextprotocol.io/introduction\\\" 2\\u003e/dev/null | sed 's/\\u003c[^\\u003e]*\\u003e//g' | grep -iE '(identity|auth|trust|verify|agent|security)' | head -20\\necho \\\"=== MCP ===\\\"\\ncurl -sL \\\"https://spec.modelcontextprotocol.io/\\\" 2\\u003e/dev/null | sed 's/\\u003c[^\\u003e]*\\u003e//g' | grep -iE '(auth|identity|trust|security)' | head -15\",\"timeout\":15}" } }, { "id": "call_3gq029nb", "call_id": "call_3gq029nb", "response_item_id": "fc_3gq029nb", "type": "function", "function": { "name": "terminal", "arguments": "{\"command\":\"curl -sL \\\"https://en.wikipedia.org/wiki/AI_agent\\\" 2\\u003e/dev/null | sed 's/\\u003c[^\\u003e]*\\u003e//g' | grep -iE '(identity|trust|liability|authorization|autonomous|legal)' | head -20\\necho \\\"=== EU AI Act ===\\\"\\ncurl -sL \\\"https://en.wikipedia.org/wiki/Artificial_Intelligence_Act\\\" 2\\u003e/dev/null | sed 's/\\u003c[^\\u003e]*\\u003e//g' | grep -iE '(agent|identity|liability|transparency|high.risk)' | head -20\",\"timeout\":15}" } } ], "finish_reason": "tool_calls", "reasoning": "Der Subagent ist nach 600 Sekunden mit einem Timeout abgestürzt, hat aber 27 API-Calls gemacht. Ich muss die Recherche selbst durchführen, aber effizienter — mehrere parallele Searches, dann synthetisieren.\n\nIch mache jetzt mehrere parallele web searches zu den wichtigsten Themen und synthetisiere dann das WhitePaper.", "reasoning_content": "Der Subagent ist nach 600 Sekunden mit einem Timeout abgestürzt, hat aber 27 API-Calls gemacht. Ich muss die Recherche selbst durchführen, aber effizienter — mehrere parallele Searches, dann synthetisieren.\n\nIch mache jetzt mehrere parallele web searches zu den wichtigsten Themen und synthetisiere dann das WhitePaper." }, { "role": "tool", "content": "{\"output\": \"GitHub - a2aproject/A2A: Agent2Agent (A2A) is an open protocol enabling communication and interoperability between opaque agentic applications. · GitHub\\n\\n\\n\\n=== A2A ===\\n 'google-auth-library-java': 'googleapis',\\n 'google-auth-library-nodejs': 'googleapis',\\n 'google-oauth-java-client': 'googleapis',\\n 'oauth2client': 'googleapis',\", \"exit_code\": 0, \"error\": null}", "tool_call_id": "call_lmgesdjb" }, { "role": "tool", "content": "{\"output\": \")Model Context Protocol home pageSearch...⌘KAsk AssistantBlogGitHubSearch...NavigationGet startedWhat is the Model Context Protocol (MCP)?DocumentationExtensionsSpecificationRegistrySEPsCommunityGet startedWhat is MCP?About MCPArchitectureServersClientsVersioningDevelop with MCPConnect to local MCP serversConnect to remote MCP ServersBuild with Agent SkillsBuild an MCP serverClientsSDKsSecurityDeveloper toolsMCP InspectorDebuggingExamplesExample Servers(function () {\\nAgents can access your Google Calendar and Notion, acting as a more personalized AI assistant.\\nDevelopers: MCP reduces development time and complexity when building, or integrating with, an AI application or agent.\\nAI applications or agents: MCP provides access to an ecosystem of data sources, tools and apps which will enhance capabilities and improve the end-user experience.\\nEnd-users: MCP results in more capable AI applications or agents which can access your data and take actions on your behalf when necessary.\\nUnderstand conceptsLearn the core concepts and architecture of MCPWas this page helpful?YesNoArchitecture⌘IgithubAssistantResponses are generated using AI and may contain mistakes.(self.__next_f=self.__next_f||[]).push([0])self.__next_f.push([1,\\\"1:\\\\\\\"$Sreact.fragment\\\\\\\"\\\\n2:I[339756,[\\\\\\\"/mintlify-assets/_next/static/chunks/de15d9642f7c974c.js?dpl=dpl_9mrFr5UWMK5pxeNnU84RRgGDfeCV\\\\\\\",\\\\\\\"/mintlify-assets/_next/static/chunks/b664fc8bb1e7ab0d.js?dpl=dpl_9mrFr5UWMK5pxeNnU84RRgGDfeCV\\\\\\\"],\\\\\\\"default\\\\\\\"]\\\\n\\\"])self.__next_f.push([1,\\\"3:I[556357,[\\\\\\\"/mintlify-assets/_next/static/chunks/de15d9642f7c974c.js?dpl=dpl_9mrFr5UWMK5pxeNnU84RRgGDfeCV\\\\\\\",\\\\\\\"/mintlify-assets/_next/static/chunks/b664fc8bb1e7ab0d.js?dpl=dpl_9mrFr5UWMK5pxeNnU84RRgGDfeCV\\\\\\\",\\\\\\\"/mintlify-assets/_next/static/chunks/22bd90086d67b03b.js?dpl=dpl_9mrFr5UWMK5pxeNnU84RRgGDfeCV\\\\\\\",\\\\\\\"/mintlify-assets/_next/static/chunks/e7e2d9fa0f487835.js?dpl=dpl_9mrFr5UWMK5pxeNnU84RRgGDfeCV\\\\\\\",\\\\\\\"/mintlify-assets/_next/static/chunks/90079180db6f14a4.js?dpl=dpl_9mrFr5UWMK5pxeNnU84RRgGDfeCV\\\\\\\",\\\\\\\"/mintlify-assets/_next/static/chunks/2354db16bc38bd45.js?dpl=dpl_9mrFr5UWMK5pxeNnU84RRgGDfeCV\\\\\\\",\\\\\\\"/mintlify-assets/_next/static/chunks/55341d0a0dea6975.js?dpl=dpl_9mrFr5UWMK5pxeNnU84RRgGDfeCV\\\\\\\",\\\\\\\"/mintlify-assets/_next/static/chunks/8b6615c03f337a0f.js?dpl=dpl_9mrFr5UWMK5pxeNnU84RRgGDfeCV\\\\\\\",\\\\\\\"/mintlify-assets/_next/static/chunks/6fd3acb5d5a9a0e5.js?dpl=dpl_9mrFr5UWMK5pxeNnU84RRgGDfeCV\\\\\\\",\\\\\\\"/mintlify-assets/_next/static/chunks/13ebb4257dd3a545.js?dpl=dpl_9mrFr5UWMK5pxeNnU84RRgGDfeCV\\\\\\\",\\\\\\\"/mintlify-assets/_next/static/chunks/bdb898abfe5bae4d.js?dpl=dpl_9mrFr5UWMK5pxeNnU84RRgGDfeCV\\\\\\\"],\\\\\\\"default\\\\\\\",1]\\\\n\\\"])self.__next_f.push([1,\\\"10:I[168027,[\\\\\\\"/mintlify-assets/_next/static/chunks/de15d9642f7c974c.js?dpl=dpl_9mrFr5UWMK5pxeNnU84RRgGDfeCV\\\\\\\",\\\\\\\"/mintlify-assets/_next/static/chunks/b664fc8bb1e7ab0d.js?dpl=dpl_9mrFr5UWMK5pxeNnU84RRgGDfeCV\\\\\\\"],\\\\\\\"default\\\\\\\"]\\\\n13:I[837457,[\\\\\\\"/mintlify-assets/_next/static/chunks/de15d9642f7c974c.js?dpl=dpl_9mrFr5UWMK5pxeNnU84RRgGDfeCV\\\\\\\",\\\\\\\"/mintlify-assets/_next/static/chunks/b664fc8bb1e7ab0d.js?dpl=dpl_9mrFr5UWMK5pxeNnU84RRgGDfeCV\\\\\\\"],\\\\\\\"default\\\\\\\"]\\\\n\\\"])self.__next_f.push([1,\\\"14:I[894587,[\\\\\\\"/mintlify-assets/_next/static/chunks/de15d9642f7c974c.js?dpl=dpl_9mrFr5UWMK5pxeNnU84RRgGDfeCV\\\\\\\",\\\\\\\"/mintlify-assets/_next/static/chunks/b664fc8bb1e7ab0d.js?dpl=dpl_9mrFr5UWMK5pxeNnU84RRgGDfeCV\\\\\\\",\\\\\\\"/mintlify-assets/_next/static/chunks/d53146a6ec2c0f8b.js?dpl=dpl_9mrFr5UWMK5pxeNnU84RRgGDfeCV\\\\\\\",\\\\\\\"/mintlify-assets/_next/static/chunks/07eb678ee01a9cdf.js?dpl=dpl_9mrFr5UWMK5pxeNnU84RRgGDfeCV\\\\\\\",\\\\\\\"/mintlify-assets/_next/static/chunks/90079180db6f14a4.js?dpl=dpl_9mrFr5UWMK5pxeNnU84RRgGDfeCV\\\\\\\",\\\\\\\"/mintlify-assets/_next/static/chunks/20315bd191e31d95.js?dpl=dpl_9mrFr5UWMK5pxeNnU84RRgGDfeCV\\\\\\\",\\\\\\\"/mintlify-assets/_next/static/chunks/247f8594ded6e6f1.js?dpl=dpl_9mrFr5UWMK5pxeNnU84RRgGDfeCV\\\\\\\",\\\\\\\"/mintlify-assets/_next/static/chunks/7285fd2749e1c6b9.js?dpl=dpl_9mrFr5UWMK5pxeNnU84RRgGDfeCV\\\\\\\",\\\\\\\"/mintlify-assets/_next/static/chunks/6fd3acb5d5a9a0e5.js?dpl=dpl_9mrFr5UWMK5pxeNnU84RRgGDfeCV\\\\\\\",\\\\\\\"/mintlify-assets/_next/static/chunks/bdb898abfe5bae4d.js?dpl=dpl_9mrFr5UWMK5pxeNnU84RRgGDfeCV\\\\\\\",\\\\\\\"/mintlify-assets/_next/static/chunks/2fc1f5c43394028e.js?dpl=dpl_9mrFr5UWMK5pxeNnU84RRgGDfeCV\\\\\\\",\\\\\\\"/mintlify-assets/_next/static/chunks/7c9afa3b141cfe13.js?dpl=dpl_9mrFr5UWMK5pxeNnU84RRgGDfeCV\\\\\\\",\\\\\\\"/mintlify-assets/_next/static/chunks/8b6615c03f337a0f.js?dpl=dpl_9mrFr5UWMK5pxeNnU84RRgGDfeCV\\\\\\\",\\\\\\\"/mintlify-assets/_next/static/chunks/50537af49df8455c.js?dpl=dpl_9mrFr5UWMK5pxeNnU84RRgGDfeCV\\\\\\\",\\\\\\\"/mintlify-assets/_next/static/chunks/078c9305541786f7.js?dpl=dpl_9mrFr5UWMK5pxeNnU84RRgGDfeCV\\\\\\\",\\\\\\\"/mintlify-assets/_next/static/chunks/13ebb4257dd3a545.js?dpl=dpl_9mrFr5UWMK5pxeNnU84RRgGDfeCV\\\\\\\",\\\\\\\"/mintlify-assets/_next/static/chunks/64862fad85696d7c.js?dpl=dpl_9mrFr5UWMK5pxeNnU84RRgGDfeCV\\\\\\\",\\\\\\\"/mintlify-assets/_next/static/chunks/67864c9d5997176d.js?dpl=dpl_9mrFr5UWMK5pxeNnU84RRgGDfeCV\\\\\\\",\\\\\\\"/mintlify-assets/_next/static/chunks/55341d0a0dea6975.js?dpl=dpl_9mrFr5UWMK5pxeNnU84RRgGDfeCV\\\\\\\",\\\\\\\"/mintlify-assets/_next/static/chunks/190e2d29d3b2239b.js?dpl=dpl_9mrFr5UWMK5pxeNnU84RRgGDfeCV\\\\\\\"],\\\\\\\"ThemeProvider\\\\\\\",1]\\\\n\\\"])self.__next_f.push([1,\\\"15:I[152823,[\\\\\\\"/mintlify-assets/_next/static/chunks/de15d9642f7c974c.js?dpl=dpl_9mrFr5UWMK5pxeNnU84RRgGDfeCV\\\\\\\",\\\\\\\"/mintlify-assets/_next/static/chunks/b664fc8bb1e7ab0d.js?dpl=dpl_9mrFr5UWMK5pxeNnU84RRgGDfeCV\\\\\\\",\\\\\\\"/mintlify-assets/_next/static/chunks/d53146a6ec2c0f8b.js?dpl=dpl_9mrFr5UWMK5pxeNnU84RRgGDfeCV\\\\\\\",\\\\\\\"/mintlify-assets/_next/static/chunks/07eb678ee01a9cdf.js?dpl=dpl_9mrFr5UWMK5pxeNnU84RRgGDfeCV\\\\\\\",\\\\\\\"/mintlify-assets/_next/static/chunks/90079180db6f14a4.js?dpl=dpl_9mrFr5UWMK5pxeNnU84RRgGDfeCV\\\\\\\",\\\\\\\"/mintlify-assets/_next/static/chunks/20315bd191e31d95.js?dpl=dpl_9mrFr5UWMK5pxeNnU84RRgGDfeCV\\\\\\\",\\\\\\\"/mintlify-assets/_next/static/chunks/247f8594ded6e6f1.js?dpl=dpl_9mrFr5UWMK5pxeNnU84RRgGDfeCV\\\\\\\",\\\\\\\"/mintlify-assets/_next/static/chunks/7285fd2749e1c6b9.js?dpl=dpl_9mrFr5UWMK5pxeNnU84RRgGDfeCV\\\\\\\",\\\\\\\"/mintlify-assets/_next/static/chunks/6fd3acb5d5a9a0e5.js?dpl=dpl_9mrFr5UWMK5pxeNnU84RRgGDfeCV\\\\\\\",\\\\\\\"/mintlify-assets/_next/static/chunks/bdb898abfe5bae4d.js?dpl=dpl_9mrFr5UWMK5pxeNnU84RRgGDfeCV\\\\\\\",\\\\\\\"/mintlify-assets/_next/static/chunks/2fc1f5c43394028e.js?dpl=dpl_9mrFr5UWMK5pxeNnU84RRgGDfeCV\\\\\\\",\\\\\\\"/mintlify-assets/_next/static/chunks/7c9afa3b141cfe13.js?dpl=dpl_9mrFr5UWMK5pxeNnU84RRgGDfeCV\\\\\\\",\\\\\\\"/mintlify-assets/_next/static/chunks/8b6615c03f337a0f.js?dpl=dpl_9mrFr5UWMK5pxeNnU84RRgGDfeCV\\\\\\\",\\\\\\\"/mintlify-assets/_next/static/chunks/50537af49df8455c.js?dpl=dpl_9mrFr5UWMK5pxeNnU84RRgGDfeCV\\\\\\\",\\\\\\\"/mintlify-assets/_next/static/chunks/078c9305541786f7.js?dpl=dpl_9mrFr5UWMK5pxeNnU84RRgGDfeCV\\\\\\\",\\\\\\\"/mintlify-assets/_next/static/chunks/13ebb4257dd3a545.js?dpl=dpl_9mrFr5UWMK5pxeNnU84RRgGDfeCV\\\\\\\",\\\\\\\"/mintlify-assets/_next/static/chunks/64862fad85696d7c.js?dpl=dpl_9mrFr5UWMK5pxeNnU84RRgGDfeCV\\\\\\\",\\\\\\\"/mintlify-assets/_next/static/chunks/67864c9d5997176d.js?dpl=dpl_9mrFr5UWMK5pxeNnU84RRgGDfeCV\\\\\\\",\\\\\\\"/mintlify-assets/_next/static/chunks/55341d0a0dea6975.js?dpl=dpl_9mrFr5UWMK5pxeNnU84RRgGDfeCV\\\\\\\",\\\\\\\"/mintlify-assets/_next/static/chunks/190e2d29d3b2239b.js?dpl=dpl_9mrFr5UWMK5pxeNnU84RRgGDfeCV\\\\\\\"],\\\\\\\"ColorVariables\\\\\\\",1]\\\\n\\\"])self.__next_f.push([1,\\\"16:I[531961,[\\\\\\\"/mintlify-assets/_next/static/chunks/de15d9642f7c974c.js?dpl=dpl_9mrFr5UWMK5pxeNnU84RRgGDfeCV\\\\\\\",\\\\\\\"/mintlify-assets/_next/static/chunks/b664fc8bb1e7ab0d.js?dpl=dpl_9mrFr5UWMK5pxeNnU84RRgGDfeCV\\\\\\\",\\\\\\\"/mintlify-assets/_next/static/chunks/d53146a6ec2c0f8b.js?dpl=dpl_9mrFr5UWMK5pxeNnU84RRgGDfeCV\\\\\\\",\\\\\\\"/mintlify-assets/_next/static/chunks/07eb678ee01a9cdf.js?dpl=dpl_9mrFr5UWMK5pxeNnU84RRgGDfeCV\\\\\\\",\\\\\\\"/mintlify-assets/_next/static/chunks/90079180db6f14a4.js?dpl=dpl_9mrFr5UWMK5pxeNnU84RRgGDfeCV\\\\\\\",\\\\\\\"/mintlify-assets/_next/static/chunks/20315bd191e31d95.js?dpl=dpl_9mrFr5UWMK5pxeNnU84RRgGDfeCV\\\\\\\",\\\\\\\"/mintlify-assets/_next/static/chunks/247f8594ded6e6f1.js?dpl=dpl_9mrFr5UWMK5pxeNnU84RRgGDfeCV\\\\\\\",\\\\\\\"/mintlify-assets/_next/static/chunks/7285fd2749e1c6b9.js?dpl=dpl_9mrFr5UWMK5pxeNnU84RRgGDfeCV\\\\\\\",\\\\\\\"/mintlify-assets/_next/static/chunks/6fd3acb5d5a9a0e5.js?dpl=dpl_9mrFr5UWMK5pxeNnU84RRgGDfeCV\\\\\\\",\\\\\\\"/mintlify-assets/_next/static/chunks/bdb898abfe5bae4d.js?dpl=dpl_9mrFr5UWMK5pxeNnU84RRgGDfeCV\\\\\\\",\\\\\\\"/mintlify-assets/_next/static/chunks/2fc1f5c43394028e.js?dpl=dpl_9mrFr5UWMK5pxeNnU84RRgGDfeCV\\\\\\\",\\\\\\\"/mintlify-assets/_next/static/chunks/7c9afa3b141cfe13.js?dpl=dpl_9mrFr5UWMK5pxeNnU84RRgGDfeCV\\\\\\\",\\\\\\\"/mintlify-assets/_next/static/chunks/8b6615c03f337a0f.js?dpl=dpl_9mrFr5UWMK5pxeNnU84RRgGDfeCV\\\\\\\",\\\\\\\"/mintlify-assets/_next/static/chunks/50537af49df8455c.js?dpl=dpl_9mrFr5UWMK5pxeNnU84RRgGDfeCV\\\\\\\",\\\\\\\"/mintlify-assets/_next/static/chunks/078c9305541786f7.js?dpl=dpl_9mrFr5UWMK5pxeNnU84RRgGDfeCV\\\\\\\",\\\\\\\"/mintlify-assets/_next/static/chunks/13ebb4257dd3a545.js?dpl=dpl_9mrFr5UWMK5pxeNnU84RRgGDfeCV\\\\\\\",\\\\\\\"/mintlify-assets/_next/static/chunks/64862fad85696d7c.js?dpl=dpl_9mrFr5UWMK5pxeNnU84RRgGDfeCV\\\\\\\",\\\\\\\"/mintlify-assets/_next/static/chunks/67864c9d5997176d.js?dpl=dpl_9mrFr5UWMK5pxeNnU84RRgGDfeCV\\\\\\\",\\\\\\\"/mintlify-assets/_next/static/chunks/55341d0a0dea6975.js?dpl=dpl_9mrFr5UWMK5pxeNnU84RRgGDfeCV\\\\\\\",\\\\\\\"/mintlify-assets/_next/static/chunks/190e2d29d3b2239b.js?dpl=dpl_9mrFr5UWMK5pxeNnU84RRgGDfeCV\\\\\\\"],\\\\\\\"FontScript\\\\\\\",1]\\\\n\\\"])self.__next_f.push([1,\\\"17:I[649328,[\\\\\\\"/mintlify-assets/_next/static/chunks/de15d9642f7c974c.js?dpl=dpl_9mrFr5UWMK5pxeNnU84RRgGDfeCV\\\\\\\",\\\\\\\"/mintlify-assets/_next/static/chunks/b664fc8bb1e7ab0d.js?dpl=dpl_9mrFr5UWMK5pxeNnU84RRgGDfeCV\\\\\\\",\\\\\\\"/mintlify-assets/_next/static/chunks/d53146a6ec2c0f8b.js?dpl=dpl_9mrFr5UWMK5pxeNnU84RRgGDfeCV\\\\\\\",\\\\\\\"/mintlify-assets/_next/static/chunks/07eb678ee01a9cdf.js?dpl=dpl_9mrFr5UWMK5pxeNnU84RRgGDfeCV\\\\\\\",\\\\\\\"/mintlify-assets/_next/static/chunks/90079180db6f14a4.js?dpl=dpl_9mrFr5UWMK5pxeNnU84RRgGDfeCV\\\\\\\",\\\\\\\"/mintlify-assets/_next/static/chunks/20315bd191e31d95.js?dpl=dpl_9mrFr5UWMK5pxeNnU84RRgGDfeCV\\\\\\\",\\\\\\\"/mintlify-assets/_next/static/chunks/247f8594ded6e6f1.js?dpl=dpl_9mrFr5UWMK5pxeNnU84RRgGDfeCV\\\\\\\",\\\\\\\"/mintlify-assets/_next/static/chunks/7285fd2749e1c6b9.js?dpl=dpl_9mrFr5UWMK5pxeNnU84RRgGDfeCV\\\\\\\",\\\\\\\"/mintlify-assets/_next/static/chunks/6fd3acb5d5a9a0e5.js?dpl=dpl_9mrFr5UWMK5pxeNnU84RRgGDfeCV\\\\\\\",\\\\\\\"/mintlify-assets/_next/static/chunks/bdb898abfe5bae4d.js?dpl=dpl_9mrFr5UWMK5pxeNnU84RRgGDfeCV\\\\\\\",\\\\\\\"/mintlify-assets/_next/static/chunks/2fc1f5c43394028e.js?dpl=dpl_9mrFr5UWMK5pxeNnU84RRgGDfeCV\\\\\\\",\\\\\\\"/mintlify-assets/_next/static/chunks/7c9afa3b141cfe13.js?dpl=dpl_9mrFr5UWMK5pxeNnU84RRgGDfeCV\\\\\\\",\\\\\\\"/mintlify-assets/_next/static/chunks/8b6615c03f337a0f.js?dpl=dpl_9mrFr5UWMK5pxeNnU84RRgGDfeCV\\\\\\\",\\\\\\\"/mintlify-assets/_next/static/chunks/50537af49df8455c.js?dpl=dpl_9mrFr5UWMK5pxeNnU84RRgGDfeCV\\\\\\\",\\\\\\\"/mintlify-assets/_next/static/chunks/078c9305541786f7.js?dpl=dpl_9mrFr5UWMK5pxeNnU84RRgGDfeCV\\\\\\\",\\\\\\\"/mintlify-assets/_next/static/chunks/13ebb4257dd3a545.js?dpl=dpl_9mrFr5UWMK5pxeNnU84RRgGDfeCV\\\\\\\",\\\\\\\"/mintlify-assets/_next/static/chunks/64862fad85696d7c.js?dpl=dpl_9mrFr5UWMK5pxeNnU84RRgGDfeCV\\\\\\\",\\\\\\\"/mintlify-assets/_next/static/chunks/67864c9d5997176d.js?dpl=dpl_9mrFr5UWMK5pxeNnU84RRgGDfeCV\\\\\\\",\\\\\\\"/mintlify-assets/_next/static/chunks/55341d0a0dea6975.js?dpl=dpl_9mrFr5UWMK5pxeNnU84RRgGDfeCV\\\\\\\",\\\\\\\"/mintlify-assets/_next/static/chunks/190e2d29d3b2239b.js?dpl=dpl_9mrFr5UWMK5pxeNnU84RRgGDfeCV\\\\\\\"],\\\\\\\"RoundedVariables\\\\\\\",1]\\\\n\\\"])self.__next_f.push([1,\\\"18:I[702910,[\\\\\\\"/mintlify-assets/_next/static/chunks/de15d9642f7c974c.js?dpl=dpl_9mrFr5UWMK5pxeNnU84RRgGDfeCV\\\\\\\",\\\\\\\"/mintlify-assets/_next/static/chunks/b664fc8bb1e7ab0d.js?dpl=dpl_9mrFr5UWMK5pxeNnU84RRgGDfeCV\\\\\\\",\\\\\\\"/mintlify-assets/_next/static/chunks/41d00935d8e95e9b.js?dpl=dpl_9mrFr5UWMK5pxeNnU84RRgGDfeCV\\\\\\\",\\\\\\\"/mintlify-assets/_next/static/chunks/e7e2d9fa0f487835.js?dpl=dpl_9mrFr5UWMK5pxeNnU84RRgGDfeCV\\\\\\\",\\\\\\\"/mintlify-assets/_next/static/chunks/6fd3acb5d5a9a0e5.js?dpl=dpl_9mrFr5UWMK5pxeNnU84RRgGDfeCV\\\\\\\",\\\\\\\"/mintlify-assets/_next/static/chunks/90079180db6f14a4.js?dpl=dpl_9mrFr5UWMK5pxeNnU84RRgGDfeCV\\\\\\\",\\\\\\\"/mintlify-assets/_next/static/chunks/bdb898abfe5bae4d.js?dpl=dpl_9mrFr5UWMK5pxeNnU84RRgGDfeCV\\\\\\\",\\\\\\\"/mintlify-assets/_next/static/chunks/8b6615c03f337a0f.js?dpl=dpl_9mrFr5UWMK5pxeNnU84RRgGDfeCV\\\\\\\",\\\\\\\"/mintlify-assets/_next/static/chunks/55341d0a0dea6975.js?dpl=dpl_9mrFr5UWMK5pxeNnU84RRgGDfeCV\\\\\\\",\\\\\\\"/mintlify-assets/_next/static/chunks/13ebb4257dd3a545.js?dpl=dpl_9mrFr5UWMK5pxeNnU84RRgGDfeCV\\\\\\\",\\\\\\\"/mintlify-assets/_next/static/chunks/2354db16bc38bd45.js?dpl=dpl_9mrFr5UWMK5pxeNnU84RRgGDfeCV\\\\\\\"],\\\\\\\"RecommendedPagesList\\\\\\\"]\\\\n\\\"])self.__next_f.push([1,\\\"19:I[570420,[\\\\\\\"/mintlify-assets/_next/static/chunks/de15d9642f7c974c.js?dpl=dpl_9mrFr5UWMK5pxeNnU84RRgGDfeCV\\\\\\\",\\\\\\\"/mintlify-assets/_next/static/chunks/b664fc8bb1e7ab0d.js?dpl=dpl_9mrFr5UWMK5pxeNnU84RRgGDfeCV\\\\\\\"],\\\\\\\"DataCurrentPathUpdater\\\\\\\"]\\\\n\\\"])self.__next_f.push([1,\\\"1a:I[341175,[\\\\\\\"/mintlify-assets/_next/static/chunks/de15d9642f7c974c.js?dpl=dpl_9mrFr5UWMK5pxeNnU84RRgGDfeCV\\\\\\\",\\\\\\\"/mintlify-assets/_next/static/chunks/b664fc8bb1e7ab0d.js?dpl=dpl_9mrFr5UWMK5pxeNnU84RRgGDfeCV\\\\\\\",\\\\\\\"/mintlify-assets/_next/static/chunks/abdf87c41ecc6f4b.js?dpl=dpl_9mrFr5UWMK5pxeNnU84RRgGDfeCV\\\\\\\",\\\\\\\"/mintlify-assets/_next/static/chunks/e7e2d9fa0f487835.js?dpl=dpl_9mrFr5UWMK5pxeNnU84RRgGDfeCV\\\\\\\",\\\\\\\"/mintlify-assets/_next/static/chunks/90079180db6f14a4.js?dpl=dpl_9mrFr5UWMK5pxeNnU84RRgGDfeCV\\\\\\\",\\\\\\\"/mintlify-assets/_next/static/chunks/2354db16bc38bd45.js?dpl=dpl_9mrFr5UWMK5pxeNnU84RRgGDfeCV\\\\\\\",\\\\\\\"/mintlify-assets/_next/static/chunks/55341d0a0dea6975.js?dpl=dpl_9mrFr5UWMK5pxeNnU84RRgGDfeCV\\\\\\\",\\\\\\\"/mintlify-assets/_next/static/chunks/8b6615c03f337a0f.js?dpl=dpl_9mrFr5UWMK5pxeNnU84RRgGDfeCV\\\\\\\",\\\\\\\"/mintlify-assets/_next/static/chunks/6fd3acb5d5a9a0e5.js?dpl=dpl_9mrFr5UWMK5pxeNnU84RRgGDfeCV\\\\\\\",\\\\\\\"/mintlify-assets/_next/static/chunks/13ebb4257dd3a545.js?dpl=dpl_9mrFr5UWMK5pxeNnU84RRgGDfeCV\\\\\\\",\\\\\\\"/mintlify-assets/_next/static/chunks/bdb898abfe5bae4d.js?dpl=dpl_9mrFr5UWMK5pxeNnU84RRgGDfeCV\\\\\\\"],\\\\\\\"default\\\\\\\",1]\\\\n\\\"])self.__next_f.push([1,\\\"1d:I[897367,[\\\\\\\"/mintlify-assets/_next/static/chunks/de15d9642f7c974c.js?dpl=dpl_9mrFr5UWMK5pxeNnU84RRgGDfeCV\\\\\\\",\\\\\\\"/mintlify-assets/_next/static/chunks/b664fc8bb1e7ab0d.js?dpl=dpl_9mrFr5UWMK5pxeNnU84RRgGDfeCV\\\\\\\"],\\\\\\\"OutletBoundary\\\\\\\"]\\\\n1f:I[711533,[\\\\\\\"/mintlify-assets/_next/static/chunks/de15d9642f7c974c.js?dpl=dpl_9mrFr5UWMK5pxeNnU84RRgGDfeCV\\\\\\\",\\\\\\\"/mintlify-assets/_next/static/chunks/b664fc8bb1e7ab0d.js?dpl=dpl_9mrFr5UWMK5pxeNnU84RRgGDfeCV\\\\\\\"],\\\\\\\"AsyncMetadataOutlet\\\\\\\"]\\\\n21:I[897367,[\\\\\\\"/mintlify-assets/_next/static/chunks/de15d9642f7c974c.js?dpl=dpl_9mrFr5UWMK5pxeNnU84RRgGDfeCV\\\\\\\",\\\\\\\"/mintlify-assets/_next/static/chunks/b664fc8bb1e7ab0d.js?dpl=dpl_9mrFr5UWMK5pxeNnU84RRgGDfeCV\\\\\\\"],\\\\\\\"ViewportBoundary\\\\\\\"]\\\\n23:I[897367,[\\\\\\\"/mintlify-assets/_next/static/chunks/de15d9642f7c974c.js?dpl=dpl_9mrFr5UWMK5pxeNnU84RRgGDfeCV\\\\\\\",\\\\\\\"/mintlify-assets/_next/static/chunks/b664fc8bb1e7ab0d.js?dpl=dpl_9mrFr5UWMK5pxeNnU84RRgGDfeCV\\\\\\\"],\\\\\\\"MetadataBoundary\\\\\\\"]\\\\n24:\\\\\\\"$Sreact.suspense\\\\\\\"\\\\n:HL[\\\\\\\"/mintlify-assets/_next/static/chunks/9ffc684b9a12d113.css?dpl=dpl_9mrFr5UWMK5pxeNnU84RRgGDfeCV\\\\\\\",\\\\\\\"style\\\\\\\"]\\\\n:HL[\\\\\\\"/mintlify-assets/_next/static/chunks/4c8ae0e77f760f22.css?dpl=dpl_9mrFr5UWMK5pxeNnU84RRgGDfeCV\\\\\\\",\\\\\\\"style\\\\\\\"]\\\\n:HL[\\\\\\\"/mintlify-assets/_next/static/chunks/d260340e1c30c06e.css?dpl=dpl_9mrFr5UWMK5pxeNnU84RRgGDfeCV\\\\\\\",\\\\\\\"style\\\\\\\"]\\\\n\\\"])self.__next_f.push([1,\\\"0:{\\\\\\\"P\\\\\\\":null,\\\\\\\"b\\\\\\\":\\\\\\\"gTQMVIQqql2HxI5cCLcb6\\\\\\\",\\\\\\\"p\\\\\\\":\\\\\\\"/mintlify-assets\\\\\\\",\\\\\\\"c\\\\\\\":[\\\\\\\"\\\\\\\",\\\\\\\"docs\\\\\\\",\\\\\\\"getting-started\\\\\\\",\\\\\\\"intro\\\\\\\"],\\\\\\\"i\\\\\\\":false,\\\\\\\"f\\\\\\\":[[[\\\\\\\"\\\\\\\",{\\\\\\\"children\\\\\\\":[\\\\\\\"%5Fsites\\\\\\\",{\\\\\\\"children\\\\\\\":[[\\\\\\\"subdomain\\\\\\\",\\\\\\\"mcp\\\\\\\",\\\\\\\"d\\\\\\\"],{\\\\\\\"children\\\\\\\":[\\\\\\\"(multitenant)\\\\\\\",{\\\\\\\"children\\\\\\\":[[\\\\\\\"slug\\\\\\\",\\\\\\\"docs/getting-started/intro\\\\\\\",\\\\\\\"oc\\\\\\\"],{\\\\\\\"children\\\\\\\":[\\\\\\\"__PAGE__\\\\\\\",{}]}]}]}]}]},\\\\\\\"$undefined\\\\\\\",\\\\\\\"$undefined\\\\\\\",true],[\\\\\\\"\\\\\\\",[\\\\\\\"$\\\\\\\",\\\\\\\"$1\\\\\\\",\\\\\\\"c\\\\\\\",{\\\\\\\"children\\\\\\\":[[[\\\\\\\"$\\\\\\\",\\\\\\\"link\\\\\\\",\\\\\\\"0\\\\\\\",{\\\\\\\"rel\\\\\\\":\\\\\\\"stylesheet\\\\\\\",\\\\\\\"href\\\\\\\":\\\\\\\"/mintlify-assets/_next/static/chunks/9ffc684b9a12d113.css?dpl=dpl_9mrFr5UWMK5pxeNnU84RRgGDfeCV\\\\\\\",\\\\\\\"precedence\\\\\\\":\\\\\\\"next\\\\\\\",\\\\\\\"crossOrigin\\\\\\\":\\\\\\\"$undefined\\\\\\\",\\\\\\\"nonce\\\\\\\":\\\\\\\"$undefined\\\\\\\"}],[\\\\\\\"$\\\\\\\",\\\\\\\"link\\\\\\\",\\\\\\\"1\\\\\\\",{\\\\\\\"rel\\\\\\\":\\\\\\\"stylesheet\\\\\\\",\\\\\\\"href\\\\\\\":\\\\\\\"/mintlify-assets/_next/static/chunks/4c8ae0e77f760f22.css?dpl=dpl_9mrFr5UWMK5pxeNnU84RRgGDfeCV\\\\\\\",\\\\\\\"precedence\\\\\\\":\\\\\\\"next\\\\\\\",\\\\\\\"crossOrigin\\\\\\\":\\\\\\\"$undefined\\\\\\\",\\\\\\\"nonce\\\\\\\":\\\\\\\"$undefined\\\\\\\"}],[\\\\\\\"$\\\\\\\",\\\\\\\"script\\\\\\\",\\\\\\\"script-0\\\\\\\",{\\\\\\\"src\\\\\\\":\\\\\\\"/mintlify-assets/_next/static/chunks/de15d9642f7c974c.js?dpl=dpl_9mrFr5UWMK5pxeNnU84RRgGDfeCV\\\\\\\",\\\\\\\"async\\\\\\\":true,\\\\\\\"nonce\\\\\\\":\\\\\\\"$undefined\\\\\\\"}],[\\\\\\\"$\\\\\\\",\\\\\\\"script\\\\\\\",\\\\\\\"script-1\\\\\\\",{\\\\\\\"src\\\\\\\":\\\\\\\"/mintlify-assets/_next/static/chunks/b664fc8bb1e7ab0d.js?dpl=dpl_9mrFr5UWMK5pxeNnU84RRgGDfeCV\\\\\\\",\\\\\\\"async\\\\\\\":true,\\\\\\\"nonce\\\\\\\":\\\\\\\"$undefined\\\\\\\"}]],[\\\\\\\"$\\\\\\\",\\\\\\\"html\\\\\\\",null,{\\\\\\\"suppressHydrationWarning\\\\\\\":true,\\\\\\\"lang\\\\\\\":\\\\\\\"en\\\\\\\",\\\\\\\"className\\\\\\\":\\\\\\\"inter_1d81deff-module__CYM0aG__variable jetbrains_mono_e9ee6d28-module__lbFCHq__variable dark\\\\\\\",\\\\\\\"data-banner-state\\\\\\\":\\\\\\\"visible\\\\\\\",\\\\\\\"data-assistant-state\\\\\\\":\\\\\\\"closed\\\\\\\",\\\\\\\"data-page-mode\\\\\\\":\\\\\\\"none\\\\\\\",\\\\\\\"data-current-path\\\\\\\":\\\\\\\"/\\\\\\\",\\\\\\\"children\\\\\\\":[[\\\\\\\"$\\\\\\\",\\\\\\\"head\\\\\\\",null,{\\\\\\\"children\\\\\\\":[[\\\\\\\"$\\\\\\\",\\\\\\\"script\\\\\\\",null,{\\\\\\\"type\\\\\\\":\\\\\\\"text/javascript\\\\\\\",\\\\\\\"dangerouslySetInnerHTML\\\\\\\":{\\\\\\\"__html\\\\\\\":\\\\\\\"!function(){var b=\\\\\\\\\\\\\\\"\\\\\\\\\\\\\\\";\\\\\\\\nfunction a(p){if(p==null)return\\\\\\\\\\\\\\\"/\\\\\\\\\\\\\\\";p=\\\\\\\\\\\\\\\"\\\\\\\\\\\\\\\"+p;if(\\\\\\\\\\\\\\\"\\\\\\\\\\\\\\\"===p)return\\\\\\\\\\\\\\\"/\\\\\\\\\\\\\\\";return\\\\\\\\\\\\\\\"/\\\\\\\\\\\\\\\"===p.charAt(0)?p:\\\\\\\\\\\\\\\"/\\\\\\\\\\\\\\\"+p}\\\\\\\\nfunction u(p){if(p==null)return p;p=\\\\\\\\\\\\\\\"\\\\\\\\\\\\\\\"+p;if(!p||p.charAt(p.length-1)===\\\\\\\\\\\\\\\"/\\\\\\\\\\\\\\\")return p.slice(0,-1);return p}\\\\\\\\nfunction i(p){if(p==null)return p;p=\\\\\\\\\\\\\\\"\\\\\\\\\\\\\\\"+p;if(6\\\\u003c=p.length\\\\u0026\\\\u0026p.substring(p.length-6)===\\\\\\\\\\\\\\\"/index\\\\\\\\\\\\\\\")return p.substring(0,p.length-6);if(\\\\\\\\\\\\\\\"index\\\\\\\\\\\\\\\"===p)return\\\\\\\\\\\\\\\"\\\\\\\\\\\\\\\";return p}\\\\\\\\nvar p=(location.pathname||\\\\\\\\\\\\\\\"\\\\\\\\\\\\\\\").split(\\\\\\\\\\\\\\\"?\\\\\\\\\\\\\\\")[0].split(\\\\\\\\\\\\\\\"#\\\\\\\\\\\\\\\")[0]||\\\\\\\\\\\\\\\"\\\\\\\\\\\\\\\";\\\\\\\\nif(b)if(p===b)p=\\\\\\\\\\\\\\\"\\\\\\\\\\\\\\\";else if(0===p.indexOf(b+\\\\\\\\\\\\\\\"/\\\\\\\\\\\\\\\"))p=p.substring(b.length);\\\\\\\\np=a(p);p=u(p);p=i(p);p=\\\\\\\\\\\\\\\"\\\\\\\\\\\\\\\"===p||\\\\\\\\\\\\\\\"index\\\\\\\\\\\\\\\"===p?\\\\\\\\\\\\\\\"/\\\\\\\\\\\\\\\":a(p);\\\\\\\\ndocument.documentElement.setAttribute(\\\\\\\\\\\\\\\"data-current-path\\\\\\\\\\\\\\\",p);\\\\\\\\n}();\\\\\\\"}}],[\\\\\\\"$\\\\\\\",\\\\\\\"script\\\\\\\",null,{\\\\\\\"type\\\\\\\":\\\\\\\"text/javascript\\\\\\\",\\\\\\\"dangerouslySetInnerHTML\\\\\\\":{\\\\\\\"__html\\\\\\\":\\\\\\\"(function(a,b){try{let c=document.getElementById(\\\\\\\\\\\\\\\"banner\\\\\\\\\\\\\\\")?.innerText;if(c){for(let d=0;d\\\\u003clocalStorage.length;d++){let e=localStorage.key(d);if(e?.endsWith(a)\\\\u0026\\\\u0026localStorage.getItem(e)===c)return void document.documentElement.setAttribute(b,\\\\\\\\\\\\\\\"hidden\\\\\\\\\\\\\\\")}document.documentElement.setAttribute(b,\\\\\\\\\\\\\\\"visible\\\\\\\\\\\\\\\");return}for(let c=0;c\\\\u003clocalStorage.length;c++){let d=localStorage.key(c);if(d?.endsWith(a)\\\\u0026\\\\u0026localStorage.getItem(d))return void document.documentElement.setAttribute(b,\\\\\\\\\\\\\\\"hidden\\\\\\\\\\\\\\\")}document.documentElement.setAttribute(b,\\\\\\\\\\\\\\\"visible\\\\\\\\\\\\\\\")}catch(a){document.documentElement.setAttribute(b,\\\\\\\\\\\\\\\"hidden\\\\\\\\\\\\\\\")}})(\\\\\\\\n \\\\\\\\\\\\\\\"bannerDismissed\\\\\\\\\\\\\\\",\\\\\\\\n \\\\\\\\\\\\\\\"data-banner-state\\\\\\\\\\\\\\\",\\\\\\\\n)\\\\\\\"}}],false]}],[\\\\\\\"$\\\\\\\",\\\\\\\"body\\\\\\\",null,{\\\\\\\"className\\\\\\\":\\\\\\\"antialiased\\\\\\\",\\\\\\\"children\\\\\\\":[false,[\\\\\\\"$\\\\\\\",\\\\\\\"$L2\\\\\\\",null,{\\\\\\\"parallelRouterKey\\\\\\\":\\\\\\\"children\\\\\\\",\\\\\\\"error\\\\\\\":\\\\\\\"$3\\\\\\\",\\\\\\\"errorStyles\\\\\\\":[],\\\\\\\"errorScripts\\\\\\\":[[\\\\\\\"$\\\\\\\",\\\\\\\"script\\\\\\\",\\\\\\\"script-0\\\\\\\",{\\\\\\\"src\\\\\\\":\\\\\\\"/mintlify-assets/_next/static/chunks/22bd90086d67b03b.js?dpl=dpl_9mrFr5UWMK5pxeNnU84RRgGDfeCV\\\\\\\",\\\\\\\"async\\\\\\\":true}],[\\\\\\\"$\\\\\\\",\\\\\\\"script\\\\\\\",\\\\\\\"script-1\\\\\\\",{\\\\\\\"src\\\\\\\":\\\\\\\"/mintlify-assets/_next/static/chunks/e7e2d9fa0f487835.js?dpl=dpl_9mrFr5UWMK5pxeNnU84RRgGDfeCV\\\\\\\",\\\\\\\"async\\\\\\\":true}],[\\\\\\\"$\\\\\\\",\\\\\\\"script\\\\\\\",\\\\\\\"script-2\\\\\\\",{\\\\\\\"src\\\\\\\":\\\\\\\"/mintlify-assets/_next/static/chunks/90079180db6f14a4.js?dpl=dpl_9mrFr5UWMK5pxeNnU84RRgGDfeCV\\\\\\\",\\\\\\\"async\\\\\\\":true}],[\\\\\\\"$\\\\\\\",\\\\\\\"script\\\\\\\",\\\\\\\"script-3\\\\\\\",{\\\\\\\"src\\\\\\\":\\\\\\\"/mintlify-assets/_next/static/chunks/2354db16bc38bd45.js?dpl=dpl_9mrFr5UWMK5pxeNnU84RRgGDfeCV\\\\\\\",\\\\\\\"async\\\\\\\":true}],[\\\\\\\"$\\\\\\\",\\\\\\\"script\\\\\\\",\\\\\\\"script-4\\\\\\\",{\\\\\\\"src\\\\\\\":\\\\\\\"/mintlify-assets/_next/static/chunks/55341d0a0dea6975.js?dpl=dpl_9mrFr5UWMK5pxeNnU84RRgGDfeCV\\\\\\\",\\\\\\\"async\\\\\\\":true}],[\\\\\\\"$\\\\\\\",\\\\\\\"script\\\\\\\",\\\\\\\"script-5\\\\\\\",{\\\\\\\"src\\\\\\\":\\\\\\\"/mintlify-assets/_next/static/chunks/8b6615c03f337a0f.js?dpl=dpl_9mrFr5UWMK5pxeNnU84RRgGDfeCV\\\\\\\",\\\\\\\"async\\\\\\\":true}],\\\\\\\"$L4\\\\\\\",\\\\\\\"$L5\\\\\\\",\\\\\\\"$L6\\\\\\\"],\\\\\\\"template\\\\\\\":\\\\\\\"$L7\\\\\\\",\\\\\\\"templateStyles\\\\\\\":\\\\\\\"$undefined\\\\\\\",\\\\\\\"templateScripts\\\\\\\":\\\\\\\"$undefined\\\\\\\",\\\\\\\"notFound\\\\\\\":\\\\\\\"$L8\\\\\\\",\\\\\\\"forbidden\\\\\\\":\\\\\\\"$undefined\\\\\\\",\\\\\\\"unauthorized\\\\\\\":\\\\\\\"$undefined\\\\\\\"}],false,\\\\\\\"$L9\\\\\\\"]}]]}]]}],{\\\\\\\"children\\\\\\\":[\\\\\\\"%5Fsites\\\\\\\",\\\\\\\"$La\\\\\\\",{\\\\\\\"children\\\\\\\":[[\\\\\\\"subdomain\\\\\\\",\\\\\\\"mcp\\\\\\\",\\\\\\\"d\\\\\\\"],\\\\\\\"$Lb\\\\\\\",{\\\\\\\"children\\\\\\\":[\\\\\\\"(multitenant)\\\\\\\",\\\\\\\"$Lc\\\\\\\",{\\\\\\\"children\\\\\\\":[[\\\\\\\"slug\\\\\\\",\\\\\\\"docs/getting-started/intro\\\\\\\",\\\\\\\"oc\\\\\\\"],\\\\\\\"$Ld\\\\\\\",{\\\\\\\"children\\\\\\n\\n... [OUTPUT TRUNCATED - 189540 chars omitted out of 239540 total] ...\\n\\n?dpl=dpl_9mrFr5UWMK5pxeNnU84RRgGDfeCV\\\\\\\",\\\\\\\"/mintlify-assets/_next/static/chunks/90079180db6f14a4.js?dpl=dpl_9mrFr5UWMK5pxeNnU84RRgGDfeCV\\\\\\\",\\\\\\\"/mintlify-assets/_next/static/chunks/20315bd191e31d95.js?dpl=dpl_9mrFr5UWMK5pxeNnU84RRgGDfeCV\\\\\\\",\\\\\\\"/mintlify-assets/_next/static/chunks/247f8594ded6e6f1.js?dpl=dpl_9mrFr5UWMK5pxeNnU84RRgGDfeCV\\\\\\\",\\\\\\\"/mintlify-assets/_next/static/chunks/7285fd2749e1c6b9.js?dpl=dpl_9mrFr5UWMK5pxeNnU84RRgGDfeCV\\\\\\\",\\\\\\\"/mintlify-assets/_next/static/chunks/6fd3acb5d5a9a0e5.js?dpl=dpl_9mrFr5UWMK5pxeNnU84RRgGDfeCV\\\\\\\",\\\\\\\"/mintlify-assets/_next/static/chunks/bdb898abfe5bae4d.js?dpl=dpl_9mrFr5UWMK5pxeNnU84RRgGDfeCV\\\\\\\",\\\\\\\"/mintlify-assets/_next/static/chunks/2fc1f5c43394028e.js?dpl=dpl_9mrFr5UWMK5pxeNnU84RRgGDfeCV\\\\\\\",\\\\\\\"/mintlify-assets/_next/static/chunks/7c9afa3b141cfe13.js?dpl=dpl_9mrFr5UWMK5pxeNnU84RRgGDfeCV\\\\\\\",\\\\\\\"/mintlify-assets/_next/static/chunks/8b6615c03f337a0f.js?dpl=dpl_9mrFr5UWMK5pxeNnU84RRgGDfeCV\\\\\\\",\\\\\\\"/mintlify-assets/_next/static/chunks/50537af49df8455c.js?dpl=dpl_9mrFr5UWMK5pxeNnU84RRgGDfeCV\\\\\\\",\\\\\\\"/mintlify-assets/_next/static/chunks/078c9305541786f7.js?dpl=dpl_9mrFr5UWMK5pxeNnU84RRgGDfeCV\\\\\\\",\\\\\\\"/mintlify-assets/_next/static/chunks/13ebb4257dd3a545.js?dpl=dpl_9mrFr5UWMK5pxeNnU84RRgGDfeCV\\\\\\\",\\\\\\\"/mintlify-assets/_next/static/chunks/64862fad85696d7c.js?dpl=dpl_9mrFr5UWMK5pxeNnU84RRgGDfeCV\\\\\\\",\\\\\\\"/mintlify-assets/_next/static/chunks/67864c9d5997176d.js?dpl=dpl_9mrFr5UWMK5pxeNnU84RRgGDfeCV\\\\\\\",\\\\\\\"/mintlify-assets/_next/static/chunks/55341d0a0dea6975.js?dpl=dpl_9mrFr5UWMK5pxeNnU84RRgGDfeCV\\\\\\\",\\\\\\\"/mintlify-assets/_next/static/chunks/190e2d29d3b2239b.js?dpl=dpl_9mrFr5UWMK5pxeNnU84RRgGDfeCV\\\\\\\",\\\\\\\"/mintlify-assets/_next/static/chunks/24ea02e20ac4ff55.js?dpl=dpl_9mrFr5UWMK5pxeNnU84RRgGDfeCV\\\\\\\",\\\\\\\"/mintlify-assets/_next/static/chunks/a6c6878ca04474ef.js?dpl=dpl_9mrFr5UWMK5pxeNnU84RRgGDfeCV\\\\\\\",\\\\\\\"/mintlify-assets/_next/static/chunks/434a83694784c993.js?dpl=dpl_9mrFr5UWMK5pxeNnU84RRgGDfeCV\\\\\\\",\\\\\\\"/mintlify-assets/_next/static/chunks/469fb016eb621041.js?dpl=dpl_9mrFr5UWMK5pxeNnU84RRgGDfeCV\\\\\\\",\\\\\\\"/mintlify-assets/_next/static/chunks/e92309faf83811de.js?dpl=dpl_9mrFr5UWMK5pxeNnU84RRgGDfeCV\\\\\\\"],\\\\\\\"default\\\\\\\",1]\\\\n\\\"])self.__next_f.push([1,\\\"3e:[\\\\\\\"$\\\\\\\",\\\\\\\"$L49\\\\\\\",null,{\\\\\\\"enabled\\\\\\\":true,\\\\\\\"isPreview\\\\\\\":false,\\\\\\\"children\\\\\\\":[\\\\\\\"$\\\\\\\",\\\\\\\"$L4a\\\\\\\",null,{\\\\\\\"subdomain\\\\\\\":\\\\\\\"mcp\\\\\\\",\\\\\\\"hasChatPermissions\\\\\\\":true,\\\\\\\"isLoggedInCli\\\\\\\":false,\\\\\\\"assistantConfig\\\\\\\":{},\\\\\\\"starterQuestions\\\\\\\":\\\\\\\"$undefined\\\\\\\",\\\\\\\"children\\\\\\\":[[\\\\\\\"$\\\\\\\",\\\\\\\"$L4b\\\\\\\",null,{}],[\\\\\\\"$\\\\\\\",\\\\\\\"script\\\\\\\",null,{\\\\\\\"dangerouslySetInnerHTML\\\\\\\":{\\\\\\\"__html\\\\\\\":\\\\\\\"(function g(a,b,c,d){try{if(window.matchMedia(\\\\\\\\\\\\\\\"(max-width: 1024px)\\\\\\\\\\\\\\\").matches||!d){document.documentElement.style.setProperty(c,\\\\\\\\\\\\\\\"0px\\\\\\\\\\\\\\\"),document.documentElement.setAttribute(\\\\\\\\\\\\\\\"data-assistant-state\\\\\\\\\\\\\\\",\\\\\\\\\\\\\\\"closed\\\\\\\\\\\\\\\"),d||localStorage.setItem(a,\\\\\\\\\\\\\\\"false\\\\\\\\\\\\\\\");return}let e=localStorage.getItem(a);if(null===e){document.documentElement.style.setProperty(c,\\\\\\\\\\\\\\\"0px\\\\\\\\\\\\\\\"),document.documentElement.setAttribute(\\\\\\\\\\\\\\\"data-assistant-state\\\\\\\\\\\\\\\",\\\\\\\\\\\\\\\"closed\\\\\\\\\\\\\\\");return}let f=JSON.parse(e),g=localStorage.getItem(b),h=null!==g?JSON.parse(g):368;document.documentElement.style.setProperty(c,f?h+\\\\\\\\\\\\\\\"px\\\\\\\\\\\\\\\":\\\\\\\\\\\\\\\"0px\\\\\\\\\\\\\\\"),document.documentElement.setAttribute(\\\\\\\\\\\\\\\"data-assistant-state\\\\\\\\\\\\\\\",f?\\\\\\\\\\\\\\\"open\\\\\\\\\\\\\\\":\\\\\\\\\\\\\\\"closed\\\\\\\\\\\\\\\")}catch(a){document.documentElement.style.setProperty(c,\\\\\\\\\\\\\\\"0px\\\\\\\\\\\\\\\"),document.documentElement.setAttribute(\\\\\\\\\\\\\\\"data-assistant-state\\\\\\\\\\\\\\\",\\\\\\\\\\\\\\\"closed\\\\\\\\\\\\\\\")}})(\\\\\\\\n \\\\\\\\\\\\\\\"chat-assistant-sheet-open\\\\\\\\\\\\\\\",\\\\\\\\n \\\\\\\\\\\\\\\"chat-assistant-sheet-width\\\\\\\\\\\\\\\",\\\\\\\\n \\\\\\\\\\\\\\\"--assistant-sheet-width\\\\\\\\\\\\\\\",\\\\\\\\n true\\\\\\\\n )\\\\\\\"}}],false,[\\\\\\\"$\\\\\\\",\\\\\\\"$L4c\\\\\\\",null,{\\\\\\\"children\\\\\\\":[[\\\\\\\"$\\\\\\\",\\\\\\\"$L2\\\\\\\",null,{\\\\\\\"parallelRouterKey\\\\\\\":\\\\\\\"children\\\\\\\",\\\\\\\"error\\\\\\\":\\\\\\\"$undefined\\\\\\\",\\\\\\\"errorStyles\\\\\\\":\\\\\\\"$undefined\\\\\\\",\\\\\\\"errorScripts\\\\\\\":\\\\\\\"$undefined\\\\\\\",\\\\\\\"template\\\\\\\":[\\\\\\\"$\\\\\\\",\\\\\\\"$L13\\\\\\\",null,{}],\\\\\\\"templateStyles\\\\\\\":\\\\\\\"$undefined\\\\\\\",\\\\\\\"templateScripts\\\\\\\":\\\\\\\"$undefined\\\\\\\",\\\\\\\"notFound\\\\\\\":[[\\\\\\\"$\\\\\\\",\\\\\\\"$L4d\\\\\\\",null,{\\\\\\\"source\\\\\\\":\\\\\\\"multitenant\\\\\\\"}],[]],\\\\\\\"forbidden\\\\\\\":\\\\\\\"$undefined\\\\\\\",\\\\\\\"unauthorized\\\\\\\":\\\\\\\"$undefined\\\\\\\"}],\\\\\\\"$undefined\\\\\\\"]}]]}]}]\\\\n\\\"])self.__next_f.push([1,\\\"4f:T1a8a,\\\"])self.__next_f.push([1,\\\"// Spec Version Warning Banner\\\\n// Displays a warning banner on older spec versions and draft pages.\\\\n//\\\\n// Mintlify automatically loads all .js files in the docs directory,\\\\n// and it maintains a /specification/latest/* redirect that always points\\\\n// to the current latest version. We use that redirect as the source of\\\\n// truth, so this script requires no updates when a new spec version is\\\\n// published. Styling re-uses Mintlify's native callout classes.\\\\n\\\\nconst DRAFT_VERSION = \\\\\\\"draft\\\\\\\";\\\\nconst LATEST_ALIAS_PATH = \\\\\\\"/specification/latest\\\\\\\";\\\\nconst SPEC_PATH_REGEX = /\\\\\\\\/specification\\\\\\\\/([\\\\\\\\w-]+)(\\\\\\\\/.*)?$/;\\\\nconst BANNER_ATTR = \\\\\\\"data-spec-version-banner\\\\\\\";\\\\n\\\\nconst CALLOUT_CLASS_WARNING =\\\\n \\\\\\\"callout my-4 px-5 py-4 overflow-hidden rounded-2xl flex gap-3 \\\\\\\" +\\\\n \\\\\\\"border border-yellow-200 bg-yellow-50 \\\\\\\" +\\\\n \\\\\\\"dark:border-yellow-900 dark:bg-yellow-600/20 \\\\\\\" +\\\\n \\\\\\\"[\\\\u0026_[data-component-part='callout-icon']]:mt-px\\\\\\\";\\\\nconst CALLOUT_CLASS_INFO =\\\\n \\\\\\\"callout my-4 px-5 py-4 overflow-hidden rounded-2xl flex gap-3 \\\\\\\" +\\\\n \\\\\\\"border border-neutral-200 bg-neutral-50 \\\\\\\" +\\\\n \\\\\\\"dark:border-neutral-700 dark:bg-white/10\\\\\\\";\\\\nconst CONTENT_CLASS_BASE =\\\\n \\\\\\\"text-sm prose dark:prose-invert min-w-0 w-full \\\\\\\" +\\\\n \\\\\\\"[\\\\u0026_a]:!text-current [\\\\u0026_a]:border-current [\\\\u0026_strong]:!text-current \\\\\\\";\\\\nconst CONTENT_CLASS_WARNING =\\\\n CONTENT_CLASS_BASE + \\\\\\\"text-yellow-800 dark:text-yellow-300\\\\\\\";\\\\nconst CONTENT_CLASS_INFO =\\\\n CONTENT_CLASS_BASE + \\\\\\\"text-neutral-800 dark:text-neutral-300\\\\\\\";\\\\nconst ICON_WRAPPER_CLASS = \\\\\\\"mt-0.5 w-4\\\\\\\";\\\\n\\\\nconst ICON_SVG_WARNING =\\\\n '\\\\u003csvg class=\\\\\\\"flex-none size-5 text-yellow-800 dark:text-yellow-300\\\\\\\" ' +\\\\n 'fill=\\\\\\\"none\\\\\\\" viewBox=\\\\\\\"0 0 24 24\\\\\\\" stroke=\\\\\\\"currentColor\\\\\\\" stroke-width=\\\\\\\"2\\\\\\\" ' +\\\\n 'aria-label=\\\\\\\"Warning\\\\\\\"\\\\u003e' +\\\\n '\\\\u003cpath stroke-linecap=\\\\\\\"round\\\\\\\" stroke-linejoin=\\\\\\\"round\\\\\\\" ' +\\\\n 'd=\\\\\\\"M12 9v2m0 4h.01m-6.938 4h13.856c1.54 0 2.502-1.667 1.732-3L13.732 ' +\\\\n \\\\\\\"4c-.77-1.333-2.694-1.333-3.464 0L3.34 16c-.77 1.333.192 3 1.732 3z\\\\\\\" +\\\\n '\\\\\\\"\\\\u003e\\\\u003c/path\\\\u003e\\\\u003c/svg\\\\u003e';\\\\nconst ICON_SVG_INFO =\\\\n '\\\\u003csvg class=\\\\\\\"flex-none size-5 text-neutral-800 dark:text-neutral-300\\\\\\\" ' +\\\\n 'viewBox=\\\\\\\"0 0 20 20\\\\\\\" fill=\\\\\\\"currentColor\\\\\\\" aria-label=\\\\\\\"Info\\\\\\\"\\\\u003e' +\\\\n '\\\\u003cpath d=\\\\\\\"M8 0C3.58125 0 0 3.58125 0 8C0 12.4187 3.58125 16 8 ' +\\\\n \\\\\\\"16C12.4187 16 16 12.4187 16 8C16 3.58125 12.4187 0 8 0ZM8 14.5C4.41563 \\\\\\\" +\\\\n \\\\\\\"14.5 1.5 11.5841 1.5 8C1.5 4.41594 4.41563 1.5 8 1.5C11.5844 1.5 14.5 \\\\\\\" +\\\\n \\\\\\\"4.41594 14.5 8C14.5 11.5841 11.5844 14.5 8 14.5ZM9.25 10.5H8.75V7.75C8.75 \\\\\\\" +\\\\n \\\\\\\"7.3375 8.41563 7 8 7H7C6.5875 7 6.25 7.3375 6.25 7.75C6.25 8.1625 6.5875 \\\\\\\" +\\\\n \\\\\\\"8.5 7 8.5H7.25V10.5H6.75C6.3375 10.5 6 10.8375 6 11.25C6 11.6625 6.3375 \\\\\\\" +\\\\n \\\\\\\"12 6.75 12H9.25C9.66406 12 10 11.6641 10 11.25C10 10.8359 9.66563 10.5 \\\\\\\" +\\\\n \\\\\\\"9.25 10.5ZM8 6C8.55219 6 9 5.55219 9 5C9 4.44781 8.55219 4 8 4C7.44781 \\\\\\\" +\\\\n '4 7 4.44687 7 5C7 5.55313 7.44687 6 8 6Z\\\\\\\"\\\\u003e\\\\u003c/path\\\\u003e\\\\u003c/svg\\\\u003e';\\\\n\\\\nfunction parseSpecPath(pathname) {\\\\n const match = pathname.match(SPEC_PATH_REGEX);\\\\n if (!match) return null;\\\\n return { version: match[1], subPath: match[2] || \\\\\\\"\\\\\\\" };\\\\n}\\\\n\\\\nasync function resolveLatestVersion() {\\\\n const cached = sessionStorage.getItem(\\\\\\\"mcp-latest-spec-version\\\\\\\");\\\\n if (cached) return cached;\\\\n\\\\n const response = await fetch(LATEST_ALIAS_PATH, { method: \\\\\\\"HEAD\\\\\\\" });\\\\n const resolved = parseSpecPath(new URL(response.url).pathname);\\\\n const version = resolved ? resolved.version : null;\\\\n\\\\n if (version \\\\u0026\\\\u0026 version !== \\\\\\\"latest\\\\\\\") {\\\\n sessionStorage.setItem(\\\\\\\"mcp-latest-spec-version\\\\\\\", version);\\\\n }\\\\n return version;\\\\n}\\\\n\\\\nfunction createBanner(message, linkHref, linkText, isDraft) {\\\\n const banner = document.createElement(\\\\\\\"div\\\\\\\");\\\\n banner.className = isDraft ? CALLOUT_CLASS_INFO : CALLOUT_CLASS_WARNING;\\\\n banner.setAttribute(\\\\\\\"role\\\\\\\", \\\\\\\"alert\\\\\\\");\\\\n banner.setAttribute(BANNER_ATTR, \\\\\\\"\\\\\\\");\\\\n banner.setAttribute(\\\\\\\"data-callout-type\\\\\\\", isDraft ? \\\\\\\"info\\\\\\\" : \\\\\\\"warning\\\\\\\");\\\\n\\\\n const iconWrapper = document.createElement(\\\\\\\"div\\\\\\\");\\\\n iconWrapper.className = ICON_WRAPPER_CLASS;\\\\n iconWrapper.setAttribute(\\\\\\\"data-component-part\\\\\\\", \\\\\\\"callout-icon\\\\\\\");\\\\n iconWrapper.innerHTML = isDraft ? ICON_SVG_INFO : ICON_SVG_WARNING;\\\\n\\\\n const content = document.createElement(\\\\\\\"div\\\\\\\");\\\\n content.className = isDraft ? CONTENT_CLASS_INFO : CONTENT_CLASS_WARNING;\\\\n content.setAttribute(\\\\\\\"data-component-part\\\\\\\", \\\\\\\"callout-content\\\\\\\");\\\\n\\\\n const text = document.createElement(\\\\\\\"span\\\\\\\");\\\\n text.textContent = message + \\\\\\\" \\\\\\\";\\\\n\\\\n const link = document.createElement(\\\\\\\"a\\\\\\\");\\\\n link.href = linkHref;\\\\n link.textContent = linkText;\\\\n\\\\n content.appendChild(text);\\\\n content.appendChild(link);\\\\n banner.appendChild(iconWrapper);\\\\n banner.appendChild(content);\\\\n\\\\n return banner;\\\\n}\\\\n\\\\nlet inserting = false;\\\\n\\\\nasync function insertWarningBanner() {\\\\n if (inserting) return;\\\\n if (document.querySelector(`[${BANNER_ATTR}]`)) return;\\\\n\\\\n const current = parseSpecPath(window.location.pathname);\\\\n if (!current) return;\\\\n\\\\n inserting = true;\\\\n try {\\\\n const latest = await resolveLatestVersion().catch(() =\\\\u003e null);\\\\n if (!latest || current.version === latest) return;\\\\n\\\\n // Re-check after the await — a concurrent call may have already\\\\n // inserted a banner, or SPA navigation may have changed the page.\\\\n if (document.querySelector(`[${BANNER_ATTR}]`)) return;\\\\n if (parseSpecPath(window.location.pathname)?.version !== current.version)\\\\n return;\\\\n\\\\n const contentArea = document.querySelector(\\\\n \\\\\\\"#content-area, main, article, .content\\\\\\\",\\\\n );\\\\n if (!contentArea) return;\\\\n\\\\n // Mintlify redirects /specification/latest/\\\\u003csub-path\\\\u003e to the actual\\\\n // version, so users land on the equivalent page in the latest spec.\\\\n const latestHref = LATEST_ALIAS_PATH + current.subPath;\\\\n const linkText = `View the latest version (${latest})`;\\\\n\\\\n const isDraft = current.version === DRAFT_VERSION;\\\\n const message = isDraft\\\\n ? \\\\\\\"You are viewing a draft of a not-yet-finalized specification.\\\\\\\"\\\\n : `You are viewing an older version (${current.version}) of the specification.`;\\\\n\\\\n const banner = createBanner(message, latestHref, linkText, isDraft);\\\\n\\\\n // Place the banner just below the page title block. Mintlify wraps\\\\n // the H1 in \\\\u003cheader id=\\\\\\\"header\\\\\\\"\\\\u003e; fall back to a raw \\\\u003ch1\\\\u003e or the\\\\n // top of the content area.\\\\n const header =\\\\n contentArea.querySelector(\\\\\\\"header#header\\\\\\\") ||\\\\n contentArea.querySelector(\\\\\\\"h1\\\\\\\");\\\\n if (header) {\\\\n header.insertAdjacentElement(\\\\\\\"afterend\\\\\\\", banner);\\\\n } else {\\\\n contentArea.insertBefore(banner, contentArea.firstChild);\\\\n }\\\\n } finally {\\\\n inserting = false;\\\\n }\\\\n}\\\\n\\\\nif (document.readyState === \\\\\\\"loading\\\\\\\") {\\\\n document.addEventListener(\\\\\\\"DOMContentLoaded\\\\\\\", insertWarningBanner);\\\\n} else {\\\\n insertWarningBanner();\\\\n}\\\\n\\\\n// Re-insert after SPA navigation.\\\\nconst observer = new MutationObserver(() =\\\\u003e {\\\\n if (\\\\n !document.querySelector(`[${BANNER_ATTR}]`) \\\\u0026\\\\u0026\\\\n parseSpecPath(window.location.pathname)\\\\n ) {\\\\n insertWarningBanner();\\\\n }\\\\n});\\\\nobserver.observe(document.body, { childList: true, subtree: true });\\\\n\\\"])self.__next_f.push([1,\\\"47:[\\\\\\\"$\\\\\\\",\\\\\\\"$L4e\\\\\\\",null,{\\\\\\\"customJsDisabled\\\\\\\":false,\\\\\\\"jsFiles\\\\\\\":[{\\\\\\\"_id\\\\\\\":\\\\\\\"695e3c6e191f31176c7baf1d\\\\\\\",\\\\\\\"subdomain\\\\\\\":\\\\\\\"mcp\\\\\\\",\\\\\\\"filePath\\\\\\\":\\\\\\\"footer.js\\\\\\\",\\\\\\\"__v\\\\\\\":0,\\\\\\\"content\\\\\\\":\\\\\\\"// Custom footer copyright notice\\\\\\\\n(function() {\\\\\\\\n function addCopyright() {\\\\\\\\n const footer = document.querySelector('footer');\\\\\\\\n if (footer \\\\u0026\\\\u0026 !document.getElementById('lf-copyright')) {\\\\\\\\n const copyright = document.createElement('div');\\\\\\\\n copyright.id = 'lf-copyright';\\\\\\\\n copyright.innerHTML = 'Copyright © Model Context Protocol a Series of LF Projects, LLC.\\\\u003cbr\\\\u003eFor web site terms of use, trademark policy and other project policies please see \\\\u003ca href=\\\\\\\\\\\\\\\"https://lfprojects.org\\\\\\\\\\\\\\\"\\\\u003ehttps://lfprojects.org\\\\u003c/a\\\\u003e.';\\\\\\\\n footer.appendChild(copyright);\\\\\\\\n }\\\\\\\\n }\\\\\\\\n\\\\\\\\n // Run on initial load\\\\\\\\n if (document.readyState === 'loading') {\\\\\\\\n document.addEventListener('DOMContentLoaded', addCopyright);\\\\\\\\n } else {\\\\\\\\n addCopyright();\\\\\\\\n }\\\\\\\\n\\\\\\\\n // Handle SPA navigation\\\\\\\\n const observer = new MutationObserver(addCopyright);\\\\\\\\n observer.observe(document.body, { childList: true, subtree: true });\\\\\\\\n})();\\\\\\\\n\\\\\\\"},{\\\\\\\"_id\\\\\\\":\\\\\\\"69b0b75e2934b069b82c07b8\\\\\\\",\\\\\\\"subdomain\\\\\\\":\\\\\\\"mcp\\\\\\\",\\\\\\\"filePath\\\\\\\":\\\\\\\"spec-version-warning.js\\\\\\\",\\\\\\\"__v\\\\\\\":0,\\\\\\\"content\\\\\\\":\\\\\\\"$4f\\\\\\\"}]}]\\\\n\\\"])self.__next_f.push([1,\\\"52:T1e14,\\\"])self.__next_f.push([1,\\\"\\\\\\\"use strict\\\\\\\";\\\\nconst {Fragment: _Fragment, jsx: _jsx, jsxs: _jsxs} = arguments[0];\\\\nconst {useMDXComponents: _provideComponents} = arguments[0];\\\\nfunction _createMdxContent(props) {\\\\n const _components = {\\\\n a: \\\\\\\"a\\\\\\\",\\\\n li: \\\\\\\"li\\\\\\\",\\\\n p: \\\\\\\"p\\\\\\\",\\\\n strong: \\\\\\\"strong\\\\\\\",\\\\n ul: \\\\\\\"ul\\\\\\\",\\\\n ..._provideComponents(),\\\\n ...props.components\\\\n }, {Card, CardGroup, Frame, Heading, OptimizedImage} = _components;\\\\n if (!Card) _missingMdxReference(\\\\\\\"Card\\\\\\\", true);\\\\n if (!CardGroup) _missingMdxReference(\\\\\\\"CardGroup\\\\\\\", true);\\\\n if (!Frame) _missingMdxReference(\\\\\\\"Frame\\\\\\\", true);\\\\n if (!Heading) _missingMdxReference(\\\\\\\"Heading\\\\\\\", true);\\\\n if (!OptimizedImage) _missingMdxReference(\\\\\\\"OptimizedImage\\\\\\\", true);\\\\n return _jsxs(_Fragment, {\\\\n children: [_jsx(_components.p, {\\\\n children: \\\\\\\"MCP (Model Context Protocol) is an open-source standard for connecting AI applications to external systems.\\\\\\\"\\\\n }), \\\\\\\"\\\\\\\\n\\\\\\\", _jsx(_components.p, {\\\\n children: \\\\\\\"Using MCP, AI applications like Claude or ChatGPT can connect to data sources (e.g. local files, databases), tools (e.g. search engines, calculators) and workflows (e.g. specialized prompts)—enabling them to access key information and perform tasks.\\\\\\\"\\\\n }), \\\\\\\"\\\\\\\\n\\\\\\\", _jsx(_components.p, {\\\\n children: \\\\\\\"Think of MCP like a USB-C port for AI applications. Just as USB-C provides a standardized way to connect electronic devices, MCP provides a standardized way to connect AI applications to external systems.\\\\\\\"\\\\n }), \\\\\\\"\\\\\\\\n\\\\\\\", _jsx(Frame, {\\\\n children: _jsx(OptimizedImage, {\\\\n src: \\\\\\\"https://mintcdn.com/mcp/bEUxYpZqie0DsluH/images/mcp-simple-diagram.png?fit=max\\\\u0026auto=format\\\\u0026n=bEUxYpZqie0DsluH\\\\u0026q=85\\\\u0026s=35268aa0ad50b8c385913810e7604550\\\\\\\",\\\\n \\\\\\\"data-og-width\\\\\\\": \\\\\\\"3840\\\\\\\",\\\\n width: \\\\\\\"3840\\\\\\\",\\\\n \\\\\\\"data-og-height\\\\\\\": \\\\\\\"1500\\\\\\\",\\\\n height: \\\\\\\"1500\\\\\\\",\\\\n \\\\\\\"data-path\\\\\\\": \\\\\\\"images/mcp-simple-diagram.png\\\\\\\",\\\\n \\\\\\\"data-optimize\\\\\\\": \\\\\\\"true\\\\\\\",\\\\n \\\\\\\"data-opv\\\\\\\": \\\\\\\"3\\\\\\\",\\\\n srcset: \\\\\\\"https://mintcdn.com/mcp/bEUxYpZqie0DsluH/images/mcp-simple-diagram.png?w=280\\\\u0026fit=max\\\\u0026auto=format\\\\u0026n=bEUxYpZqie0DsluH\\\\u0026q=85\\\\u0026s=0cea440365b03c2f2a299b0104375b8b 280w, https://mintcdn.com/mcp/bEUxYpZqie0DsluH/images/mcp-simple-diagram.png?w=560\\\\u0026fit=max\\\\u0026auto=format\\\\u0026n=bEUxYpZqie0DsluH\\\\u0026q=85\\\\u0026s=2391513484df96fa7203739dae5e53b0 560w, https://mintcdn.com/mcp/bEUxYpZqie0DsluH/images/mcp-simple-diagram.png?w=840\\\\u0026fit=max\\\\u0026auto=format\\\\u0026n=bEUxYpZqie0DsluH\\\\u0026q=85\\\\u0026s=96f5e553bee1051dc882db6c832b15bc 840w, https://mintcdn.com/mcp/bEUxYpZqie0DsluH/images/mcp-simple-diagram.png?w=1100\\\\u0026fit=max\\\\u0026auto=format\\\\u0026n=bEUxYpZqie0DsluH\\\\u0026q=85\\\\u0026s=341b88d6308188ab06bf05748c80a494 1100w, https://mintcdn.com/mcp/bEUxYpZqie0DsluH/images/mcp-simple-diagram.png?w=1650\\\\u0026fit=max\\\\u0026auto=format\\\\u0026n=bEUxYpZqie0DsluH\\\\u0026q=85\\\\u0026s=a131a609c7b6a70f342f493bbad57fcb 1650w, https://mintcdn.com/mcp/bEUxYpZqie0DsluH/images/mcp-simple-diagram.png?w=2500\\\\u0026fit=max\\\\u0026auto=format\\\\u0026n=bEUxYpZqie0DsluH\\\\u0026q=85\\\\u0026s=dc4ab238184b6c70e06e871681c921c5 2500w\\\\\\\"\\\\n })\\\\n }), \\\\\\\"\\\\\\\\n\\\\\\\", _jsx(Heading, {\\\\n level: \\\\\\\"2\\\\\\\",\\\\n id: \\\\\\\"what-can-mcp-enable%3F\\\\\\\",\\\\n children: \\\\\\\"What can MCP enable?\\\\\\\"\\\\n }), \\\\\\\"\\\\\\\\n\\\\\\\", _jsxs(_components.ul, {\\\\n children: [\\\\\\\"\\\\\\\\n\\\\\\\", _jsx(_components.li, {\\\\n children: \\\\\\\"Agents can access your Google Calendar and Notion, acting as a more personalized AI assistant.\\\\\\\"\\\\n }), \\\\\\\"\\\\\\\\n\\\\\\\", _jsx(_components.li, {\\\\n children: \\\\\\\"Claude Code can generate an entire web app using a Figma design.\\\\\\\"\\\\n }), \\\\\\\"\\\\\\\\n\\\\\\\", _jsx(_components.li, {\\\\n children: \\\\\\\"Enterprise chatbots can connect to multiple databases across an organization, empowering users to analyze data using chat.\\\\\\\"\\\\n }), \\\\\\\"\\\\\\\\n\\\\\\\", _jsx(_components.li, {\\\\n children: \\\\\\\"AI models can create 3D designs on Blender and print them out using a 3D printer.\\\\\\\"\\\\n }), \\\\\\\"\\\\\\\\n\\\\\\\"]\\\\n }), \\\\\\\"\\\\\\\\n\\\\\\\", _jsx(Heading, {\\\\n level: \\\\\\\"2\\\\\\\",\\\\n id: \\\\\\\"why-does-mcp-matter%3F\\\\\\\",\\\\n children: \\\\\\\"Why does MCP matter?\\\\\\\"\\\\n }), \\\\\\\"\\\\\\\\n\\\\\\\", _jsx(_components.p, {\\\\n children: \\\\\\\"Depending on where you sit in the ecosystem, MCP can have a range of benefits.\\\\\\\"\\\\n }), \\\\\\\"\\\\\\\\n\\\\\\\", _jsxs(_components.ul, {\\\\n children: [\\\\\\\"\\\\\\\\n\\\\\\\", _jsxs(_components.li, {\\\\n children: [_jsx(_components.strong, {\\\\n children: \\\\\\\"Developers\\\\\\\"\\\\n }), \\\\\\\": MCP reduces development time and complexity when building, or integrating with, an AI application or agent.\\\\\\\"]\\\\n }), \\\\\\\"\\\\\\\\n\\\\\\\", _jsxs(_components.li, {\\\\n children: [_jsx(_components.strong, {\\\\n children: \\\\\\\"AI applications or agents\\\\\\\"\\\\n }), \\\\\\\": MCP provides access to an ecosystem of data sources, tools and apps which will enhance capabilities and improve the end-user experience.\\\\\\\"]\\\\n }), \\\\\\\"\\\\\\\\n\\\\\\\", _jsxs(_components.li, {\\\\n children: [_jsx(_components.strong, {\\\\n children: \\\\\\\"End-users\\\\\\\"\\\\n }), \\\\\\\": MCP results in more capable AI applications or agents which can access your data and take actions on your behalf when necessary.\\\\\\\"]\\\\n }), \\\\\\\"\\\\\\\\n\\\\\\\"]\\\\n }), \\\\\\\"\\\\\\\\n\\\\\\\", _jsx(Heading, {\\\\n level: \\\\\\\"2\\\\\\\",\\\\n id: \\\\\\\"broad-ecosystem-support\\\\\\\",\\\\n children: \\\\\\\"Broad ecosystem support\\\\\\\"\\\\n }), \\\\\\\"\\\\\\\\n\\\\\\\", _jsxs(_components.p, {\\\\n children: [\\\\\\\"MCP is an open protocol supported across a wide range of clients and servers. AI assistants like \\\\\\\", _jsx(_components.a, {\\\\n href: \\\\\\\"https://claude.com/docs/connectors/building\\\\\\\",\\\\n children: \\\\\\\"Claude\\\\\\\"\\\\n }), \\\\\\\" and \\\\\\\", _jsx(_components.a, {\\\\n href: \\\\\\\"https://developers.openai.com/api/docs/mcp/\\\\\\\",\\\\n children: \\\\\\\"ChatGPT\\\\\\\"\\\\n }), \\\\\\\", development tools like \\\\\\\", _jsx(_components.a, {\\\\n href: \\\\\\\"https://code.visualstudio.com/docs/copilot/chat/mcp-servers\\\\\\\",\\\\n children: \\\\\\\"Visual Studio Code\\\\\\\"\\\\n }), \\\\\\\", \\\\\\\", _jsx(_components.a, {\\\\n href: \\\\\\\"https://cursor.com/docs/context/mcp\\\\\\\",\\\\n children: \\\\\\\"Cursor\\\\\\\"\\\\n }), \\\\\\\", \\\\\\\", _jsx(_components.a, {\\\\n href: \\\\\\\"https://docs.mcpjam.com/getting-started\\\\\\\",\\\\n children: \\\\\\\"MCPJam\\\\\\\"\\\\n }), \\\\\\\", and many others all support MCP — making it easy to build once and integrate everywhere.\\\\\\\"]\\\\n }), \\\\\\\"\\\\\\\\n\\\\\\\", _jsx(Heading, {\\\\n level: \\\\\\\"2\\\\\\\",\\\\n id: \\\\\\\"start-building\\\\\\\",\\\\n children: \\\\\\\"Start Building\\\\\\\"\\\\n }), \\\\\\\"\\\\\\\\n\\\\\\\", _jsxs(CardGroup, {\\\\n cols: 2,\\\\n children: [_jsx(Card, {\\\\n title: \\\\\\\"Build servers\\\\\\\",\\\\n icon: \\\\\\\"server\\\\\\\",\\\\n href: \\\\\\\"/docs/develop/build-server\\\\\\\",\\\\n children: _jsx(_components.p, {\\\\n children: \\\\\\\"Create MCP servers to expose your data and tools\\\\\\\"\\\\n })\\\\n }), _jsx(Card, {\\\\n title: \\\\\\\"Build clients\\\\\\\",\\\\n icon: \\\\\\\"computer\\\\\\\",\\\\n href: \\\\\\\"/docs/develop/build-client\\\\\\\",\\\\n children: _jsx(_components.p, {\\\\n children: \\\\\\\"Develop applications that connect to MCP servers\\\\\\\"\\\\n })\\\\n }), _jsx(Card, {\\\\n title: \\\\\\\"Build MCP Apps\\\\\\\",\\\\n icon: \\\\\\\"puzzle-piece\\\\\\\",\\\\n href: \\\\\\\"/extensions/apps/overview\\\\\\\",\\\\n children: _jsx(_components.p, {\\\\n children: \\\\\\\"Build interactive apps that run inside AI clients\\\\\\\"\\\\n })\\\\n })]\\\\n }), \\\\\\\"\\\\\\\\n\\\\\\\", _jsx(Heading, {\\\\n level: \\\\\\\"2\\\\\\\",\\\\n id: \\\\\\\"learn-more\\\\\\\",\\\\n children: \\\\\\\"Learn more\\\\\\\"\\\\n }), \\\\\\\"\\\\\\\\n\\\\\\\", _jsx(CardGroup, {\\\\n cols: 2,\\\\n children: _jsx(Card, {\\\\n title: \\\\\\\"Understand concepts\\\\\\\",\\\\n icon: \\\\\\\"book\\\\\\\",\\\\n href: \\\\\\\"/docs/learn/architecture\\\\\\\",\\\\n children: _jsx(_components.p, {\\\\n children: \\\\\\\"Learn the core concepts and architecture of MCP\\\\\\\"\\\\n })\\\\n })\\\\n })]\\\\n });\\\\n}\\\\nfunction MDXContent(props = {}) {\\\\n const {wrapper: MDXLayout} = {\\\\n ..._provideComponents(),\\\\n ...props.components\\\\n };\\\\n return MDXLayout ? _jsx(MDXLayout, {\\\\n ...props,\\\\n children: _jsx(_createMdxContent, {\\\\n ...props\\\\n })\\\\n }) : _createMdxContent(props);\\\\n}\\\\nreturn {\\\\n default: MDXContent\\\\n};\\\\nfunction _missingMdxReference(id, component) {\\\\n throw new Error(\\\\\\\"Expected \\\\\\\" + (component ? \\\\\\\"component\\\\\\\" : \\\\\\\"object\\\\\\\") + \\\\\\\" `\\\\\\\" + id + \\\\\\\"` to be defined: you likely forgot to import, pass, or provide it.\\\\\\\");\\\\n}\\\\n\\\"])self.__next_f.push([1,\\\"53:T1e14,\\\"])self.__next_f.push([1,\\\"\\\\\\\"use strict\\\\\\\";\\\\nconst {Fragment: _Fragment, jsx: _jsx, jsxs: _jsxs} = arguments[0];\\\\nconst {useMDXComponents: _provideComponents} = arguments[0];\\\\nfunction _createMdxContent(props) {\\\\n const _components = {\\\\n a: \\\\\\\"a\\\\\\\",\\\\n li: \\\\\\\"li\\\\\\\",\\\\n p: \\\\\\\"p\\\\\\\",\\\\n strong: \\\\\\\"strong\\\\\\\",\\\\n ul: \\\\\\\"ul\\\\\\\",\\\\n ..._provideComponents(),\\\\n ...props.components\\\\n }, {Card, CardGroup, Frame, Heading, OptimizedImage} = _components;\\\\n if (!Card) _missingMdxReference(\\\\\\\"Card\\\\\\\", true);\\\\n if (!CardGroup) _missingMdxReference(\\\\\\\"CardGroup\\\\\\\", true);\\\\n if (!Frame) _missingMdxReference(\\\\\\\"Frame\\\\\\\", true);\\\\n if (!Heading) _missingMdxReference(\\\\\\\"Heading\\\\\\\", true);\\\\n if (!OptimizedImage) _missingMdxReference(\\\\\\\"OptimizedImage\\\\\\\", true);\\\\n return _jsxs(_Fragment, {\\\\n children: [_jsx(_components.p, {\\\\n children: \\\\\\\"MCP (Model Context Protocol) is an open-source standard for connecting AI applications to external systems.\\\\\\\"\\\\n }), \\\\\\\"\\\\\\\\n\\\\\\\", _jsx(_components.p, {\\\\n children: \\\\\\\"Using MCP, AI applications like Claude or ChatGPT can connect to data sources (e.g. local files, databases), tools (e.g. search engines, calculators) and workflows (e.g. specialized prompts)—enabling them to access key information and perform tasks.\\\\\\\"\\\\n }), \\\\\\\"\\\\\\\\n\\\\\\\", _jsx(_components.p, {\\\\n children: \\\\\\\"Think of MCP like a USB-C port for AI applications. Just as USB-C provides a standardized way to connect electronic devices, MCP provides a standardized way to connect AI applications to external systems.\\\\\\\"\\\\n }), \\\\\\\"\\\\\\\\n\\\\\\\", _jsx(Frame, {\\\\n children: _jsx(OptimizedImage, {\\\\n src: \\\\\\\"https://mintcdn.com/mcp/bEUxYpZqie0DsluH/images/mcp-simple-diagram.png?fit=max\\\\u0026auto=format\\\\u0026n=bEUxYpZqie0DsluH\\\\u0026q=85\\\\u0026s=35268aa0ad50b8c385913810e7604550\\\\\\\",\\\\n \\\\\\\"data-og-width\\\\\\\": \\\\\\\"3840\\\\\\\",\\\\n width: \\\\\\\"3840\\\\\\\",\\\\n \\\\\\\"data-og-height\\\\\\\": \\\\\\\"1500\\\\\\\",\\\\n height: \\\\\\\"1500\\\\\\\",\\\\n \\\\\\\"data-path\\\\\\\": \\\\\\\"images/mcp-simple-diagram.png\\\\\\\",\\\\n \\\\\\\"data-optimize\\\\\\\": \\\\\\\"true\\\\\\\",\\\\n \\\\\\\"data-opv\\\\\\\": \\\\\\\"3\\\\\\\",\\\\n srcset: \\\\\\\"https://mintcdn.com/mcp/bEUxYpZqie0DsluH/images/mcp-simple-diagram.png?w=280\\\\u0026fit=max\\\\u0026auto=format\\\\u0026n=bEUxYpZqie0DsluH\\\\u0026q=85\\\\u0026s=0cea440365b03c2f2a299b0104375b8b 280w, https://mintcdn.com/mcp/bEUxYpZqie0DsluH/images/mcp-simple-diagram.png?w=560\\\\u0026fit=max\\\\u0026auto=format\\\\u0026n=bEUxYpZqie0DsluH\\\\u0026q=85\\\\u0026s=2391513484df96fa7203739dae5e53b0 560w, https://mintcdn.com/mcp/bEUxYpZqie0DsluH/images/mcp-simple-diagram.png?w=840\\\\u0026fit=max\\\\u0026auto=format\\\\u0026n=bEUxYpZqie0DsluH\\\\u0026q=85\\\\u0026s=96f5e553bee1051dc882db6c832b15bc 840w, https://mintcdn.com/mcp/bEUxYpZqie0DsluH/images/mcp-simple-diagram.png?w=1100\\\\u0026fit=max\\\\u0026auto=format\\\\u0026n=bEUxYpZqie0DsluH\\\\u0026q=85\\\\u0026s=341b88d6308188ab06bf05748c80a494 1100w, https://mintcdn.com/mcp/bEUxYpZqie0DsluH/images/mcp-simple-diagram.png?w=1650\\\\u0026fit=max\\\\u0026auto=format\\\\u0026n=bEUxYpZqie0DsluH\\\\u0026q=85\\\\u0026s=a131a609c7b6a70f342f493bbad57fcb 1650w, https://mintcdn.com/mcp/bEUxYpZqie0DsluH/images/mcp-simple-diagram.png?w=2500\\\\u0026fit=max\\\\u0026auto=format\\\\u0026n=bEUxYpZqie0DsluH\\\\u0026q=85\\\\u0026s=dc4ab238184b6c70e06e871681c921c5 2500w\\\\\\\"\\\\n })\\\\n }), \\\\\\\"\\\\\\\\n\\\\\\\", _jsx(Heading, {\\\\n level: \\\\\\\"2\\\\\\\",\\\\n id: \\\\\\\"what-can-mcp-enable%3F\\\\\\\",\\\\n children: \\\\\\\"What can MCP enable?\\\\\\\"\\\\n }), \\\\\\\"\\\\\\\\n\\\\\\\", _jsxs(_components.ul, {\\\\n children: [\\\\\\\"\\\\\\\\n\\\\\\\", _jsx(_components.li, {\\\\n children: \\\\\\\"Agents can access your Google Calendar and Notion, acting as a more personalized AI assistant.\\\\\\\"\\\\n }), \\\\\\\"\\\\\\\\n\\\\\\\", _jsx(_components.li, {\\\\n children: \\\\\\\"Claude Code can generate an entire web app using a Figma design.\\\\\\\"\\\\n }), \\\\\\\"\\\\\\\\n\\\\\\\", _jsx(_components.li, {\\\\n children: \\\\\\\"Enterprise chatbots can connect to multiple databases across an organization, empowering users to analyze data using chat.\\\\\\\"\\\\n }), \\\\\\\"\\\\\\\\n\\\\\\\", _jsx(_components.li, {\\\\n children: \\\\\\\"AI models can create 3D designs on Blender and print them out using a 3D printer.\\\\\\\"\\\\n }), \\\\\\\"\\\\\\\\n\\\\\\\"]\\\\n }), \\\\\\\"\\\\\\\\n\\\\\\\", _jsx(Heading, {\\\\n level: \\\\\\\"2\\\\\\\",\\\\n id: \\\\\\\"why-does-mcp-matter%3F\\\\\\\",\\\\n children: \\\\\\\"Why does MCP matter?\\\\\\\"\\\\n }), \\\\\\\"\\\\\\\\n\\\\\\\", _jsx(_components.p, {\\\\n children: \\\\\\\"Depending on where you sit in the ecosystem, MCP can have a range of benefits.\\\\\\\"\\\\n }), \\\\\\\"\\\\\\\\n\\\\\\\", _jsxs(_components.ul, {\\\\n children: [\\\\\\\"\\\\\\\\n\\\\\\\", _jsxs(_components.li, {\\\\n children: [_jsx(_components.strong, {\\\\n children: \\\\\\\"Developers\\\\\\\"\\\\n }), \\\\\\\": MCP reduces development time and complexity when building, or integrating with, an AI application or agent.\\\\\\\"]\\\\n }), \\\\\\\"\\\\\\\\n\\\\\\\", _jsxs(_components.li, {\\\\n children: [_jsx(_components.strong, {\\\\n children: \\\\\\\"AI applications or agents\\\\\\\"\\\\n }), \\\\\\\": MCP provides access to an ecosystem of data sources, tools and apps which will enhance capabilities and improve the end-user experience.\\\\\\\"]\\\\n }), \\\\\\\"\\\\\\\\n\\\\\\\", _jsxs(_components.li, {\\\\n children: [_jsx(_components.strong, {\\\\n children: \\\\\\\"End-users\\\\\\\"\\\\n }), \\\\\\\": MCP results in more capable AI applications or agents which can access your data and take actions on your behalf when necessary.\\\\\\\"]\\\\n }), \\\\\\\"\\\\\\\\n\\\\\\\"]\\\\n }), \\\\\\\"\\\\\\\\n\\\\\\\", _jsx(Heading, {\\\\n level: \\\\\\\"2\\\\\\\",\\\\n id: \\\\\\\"broad-ecosystem-support\\\\\\\",\\\\n children: \\\\\\\"Broad ecosystem support\\\\\\\"\\\\n }), \\\\\\\"\\\\\\\\n\\\\\\\", _jsxs(_components.p, {\\\\n children: [\\\\\\\"MCP is an open protocol supported across a wide range of clients and servers. AI assistants like \\\\\\\", _jsx(_components.a, {\\\\n href: \\\\\\\"https://claude.com/docs/connectors/building\\\\\\\",\\\\n children: \\\\\\\"Claude\\\\\\\"\\\\n }), \\\\\\\" and \\\\\\\", _jsx(_components.a, {\\\\n href: \\\\\\\"https://developers.openai.com/api/docs/mcp/\\\\\\\",\\\\n children: \\\\\\\"ChatGPT\\\\\\\"\\\\n }), \\\\\\\", development tools like \\\\\\\", _jsx(_components.a, {\\\\n href: \\\\\\\"https://code.visualstudio.com/docs/copilot/chat/mcp-servers\\\\\\\",\\\\n children: \\\\\\\"Visual Studio Code\\\\\\\"\\\\n }), \\\\\\\", \\\\\\\", _jsx(_components.a, {\\\\n href: \\\\\\\"https://cursor.com/docs/context/mcp\\\\\\\",\\\\n children: \\\\\\\"Cursor\\\\\\\"\\\\n }), \\\\\\\", \\\\\\\", _jsx(_components.a, {\\\\n href: \\\\\\\"https://docs.mcpjam.com/getting-started\\\\\\\",\\\\n children: \\\\\\\"MCPJam\\\\\\\"\\\\n }), \\\\\\\", and many others all support MCP — making it easy to build once and integrate everywhere.\\\\\\\"]\\\\n }), \\\\\\\"\\\\\\\\n\\\\\\\", _jsx(Heading, {\\\\n level: \\\\\\\"2\\\\\\\",\\\\n id: \\\\\\\"start-building\\\\\\\",\\\\n children: \\\\\\\"Start Building\\\\\\\"\\\\n }), \\\\\\\"\\\\\\\\n\\\\\\\", _jsxs(CardGroup, {\\\\n cols: 2,\\\\n children: [_jsx(Card, {\\\\n title: \\\\\\\"Build servers\\\\\\\",\\\\n icon: \\\\\\\"server\\\\\\\",\\\\n href: \\\\\\\"/docs/develop/build-server\\\\\\\",\\\\n children: _jsx(_components.p, {\\\\n children: \\\\\\\"Create MCP servers to expose your data and tools\\\\\\\"\\\\n })\\\\n }), _jsx(Card, {\\\\n title: \\\\\\\"Build clients\\\\\\\",\\\\n icon: \\\\\\\"computer\\\\\\\",\\\\n href: \\\\\\\"/docs/develop/build-client\\\\\\\",\\\\n children: _jsx(_components.p, {\\\\n children: \\\\\\\"Develop applications that connect to MCP servers\\\\\\\"\\\\n })\\\\n }), _jsx(Card, {\\\\n title: \\\\\\\"Build MCP Apps\\\\\\\",\\\\n icon: \\\\\\\"puzzle-piece\\\\\\\",\\\\n href: \\\\\\\"/extensions/apps/overview\\\\\\\",\\\\n children: _jsx(_components.p, {\\\\n children: \\\\\\\"Build interactive apps that run inside AI clients\\\\\\\"\\\\n })\\\\n })]\\\\n }), \\\\\\\"\\\\\\\\n\\\\\\\", _jsx(Heading, {\\\\n level: \\\\\\\"2\\\\\\\",\\\\n id: \\\\\\\"learn-more\\\\\\\",\\\\n children: \\\\\\\"Learn more\\\\\\\"\\\\n }), \\\\\\\"\\\\\\\\n\\\\\\\", _jsx(CardGroup, {\\\\n cols: 2,\\\\n children: _jsx(Card, {\\\\n title: \\\\\\\"Understand concepts\\\\\\\",\\\\n icon: \\\\\\\"book\\\\\\\",\\\\n href: \\\\\\\"/docs/learn/architecture\\\\\\\",\\\\n children: _jsx(_components.p, {\\\\n children: \\\\\\\"Learn the core concepts and architecture of MCP\\\\\\\"\\\\n })\\\\n })\\\\n })]\\\\n });\\\\n}\\\\nfunction MDXContent(props = {}) {\\\\n const {wrapper: MDXLayout} = {\\\\n ..._provideComponents(),\\\\n ...props.components\\\\n };\\\\n return MDXLayout ? _jsx(MDXLayout, {\\\\n ...props,\\\\n children: _jsx(_createMdxContent, {\\\\n ...props\\\\n })\\\\n }) : _createMdxContent(props);\\\\n}\\\\nreturn {\\\\n default: MDXContent\\\\n};\\\\nfunction _missingMdxReference(id, component) {\\\\n throw new Error(\\\\\\\"Expected \\\\\\\" + (component ? \\\\\\\"component\\\\\\\" : \\\\\\\"object\\\\\\\") + \\\\\\\" `\\\\\\\" + id + \\\\\\\"` to be defined: you likely forgot to import, pass, or provide it.\\\\\\\");\\\\n}\\\\n\\\"])self.__next_f.push([1,\\\"48:[\\\\\\\"$\\\\\\\",\\\\\\\"$L50\\\\\\\",null,{\\\\\\\"slug\\\\\\\":\\\\\\\"docs/getting-started/intro\\\\\\\",\\\\\\\"pageMetadata\\\\\\\":\\\\\\\"$1c:props:pageMetadata\\\\\\\",\\\\\\\"theme\\\\\\\":\\\\\\\"mint\\\\\\\",\\\\\\\"children\\\\\\\":[\\\\\\\"$\\\\\\\",\\\\\\\"$L51\\\\\\\",null,{\\\\\\\"mdxSource\\\\\\\":{\\\\\\\"compiledSource\\\\\\\":\\\\\\\"$52\\\\\\\",\\\\\\\"frontmatter\\\\\\\":{},\\\\\\\"scope\\\\\\\":{\\\\\\\"config\\\\\\\":{},\\\\\\\"pageMetadata\\\\\\\":{\\\\\\\"title\\\\\\\":\\\\\\\"What is the Model Context Protocol (MCP)?\\\\\\\",\\\\\\\"sidebarTitle\\\\\\\":\\\\\\\"What is MCP?\\\\\\\",\\\\\\\"href\\\\\\\":\\\\\\\"/docs/getting-started/intro\\\\\\\"}}},\\\\\\\"mdxSourceWithNoJs\\\\\\\":{\\\\\\\"compiledSource\\\\\\\":\\\\\\\"$53\\\\\\\",\\\\\\\"frontmatter\\\\\\\":{},\\\\\\\"scope\\\\\\\":{\\\\\\\"config\\\\\\\":{},\\\\\\\"pageMetadata\\\\\\\":{\\\\\\\"title\\\\\\\":\\\\\\\"What is the Model Context Protocol (MCP)?\\\\\\\",\\\\\\\"sidebarTitle\\\\\\\":\\\\\\\"What is MCP?\\\\\\\",\\\\\\\"href\\\\\\\":\\\\\\\"/docs/getting-started/intro\\\\\\\"}}},\\\\\\\"displayDomain\\\\\\\":\\\\\\\"modelcontextprotocol.io\\\\\\\"}]}]\\\\n\\\"])\\n=== MCP ===\", \"exit_code\": 0, \"error\": null}", "tool_call_id": "call_s5lalvdj" }, { "role": "tool", "content": "{\"output\": \"