agents-docs
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
No arguments | |||
Instructions
Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.
This server publishes no instructions, or was last inspected before Glama recorded them.
Capabilities
Features and capabilities supported by this server
Protocol revision2025-11-25
| Capability | Details |
|---|---|
| tools | {
"listChanged": false
} |
| prompts | {
"listChanged": false
} |
| resources | {
"subscribe": false,
"listChanged": false
} |
| experimental | {} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| list_docsetsA | List all indexed framework/library docsets in ~/.agents/docs/ with file stats and metadata. |
| search_docsA | Search local documentation sets using header-aware BM25 lexical ranking. Auto-fetches missing catalog docsets on demand in 1 second. Args: query: Keywords, function signatures, or questions (e.g. '$state runes', 'HTTPException', 'glassmorphism') docset: Target docset name (e.g. 'svelte-5', 'fastapi', 'tailwind-v3') or 'all' to search all installed docs. top_k: Number of relevant sections to return (default 4). |
| get_doc_pageA | Fetch the complete raw markdown of a specific documentation page. Args: docset: Name of the docset (e.g. 'svelte-5') rel_path: Relative path to the markdown file within the docset (e.g. 'docs.md' or 'runes/state.md') |
| list_catalogA | List curated pre-configured framework docsets available for 1-click sync. Includes Svelte 5, FastAPI, Next.js, Supabase, Tailwind v3/v4, Tauri 2, Hono, MCP, WXT. |
| sync_docsetA | Synchronize or update a documentation set from the curated catalog or a custom URL. Args: name: Name of the catalog item (e.g. 'svelte-5', 'fastapi', 'tailwind-v3') or a custom docset identifier. url: Optional custom URL (pointing to llms.txt, llms-full.txt, or raw markdown) if name is not in catalog. |
| sync_project_docsB | Inspect a project directory (package.json, requirements.txt, pyproject.toml, Cargo.toml), detect used frameworks/libraries, and auto-sync all matching official documentation sets. Args: project_path: Absolute or relative path to project root folder |
| sync_memory_docsA | Scan local agents-memory (~/.agents/memory/PROJECTS.md & projects/*.md), detect all active tech stacks/frameworks, and auto-sync matching documentation sets. |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
TDQS
Scored across 7 tools
Each tool serves a distinct purpose: listing installed docs, searching, fetching a page, listing available catalogs, and three specific sync modes. Even the two 'list' tools are clearly separated by context (local vs catalog). No overlaps or ambiguous boundaries.
All tool names follow a consistent verb_noun pattern (list_, search_, get_, sync_, etc.). The nouns are specific and descriptive, and the use of snake_case is uniform throughout. No style mixing or vague generic names.
Seven tools is well-scoped for a documentation management server. Each tool covers a distinct aspect—listing, searching, fetching, catalog access, and syncing via three methods—without unnecessary duplication or bloat.
The toolset covers the full lifecycle of local documentation management: discover installed docs, search, retrieve content, sync from catalog or custom URL, and auto-sync based on project dependencies or memory files. No obvious missing operations for the intended purpose.