RTFD (Read The F*****g Docs)

Instructions

Implementation Reference

• src/RTFD/providers/crates.py:169-193 (handler)

  The main handler function for the 'search_crates' MCP tool. It delegates to the internal _search_crates method and serializes the response.
  async def search_crates(query: str, limit: int = 5) -> CallToolResult: """ Search for Rust crates on crates.io by name or keywords. USE THIS WHEN: You need to find Rust packages/crates for a specific purpose or library. BEST FOR: Discovering which Rust crates exist for a topic or functionality. Returns multiple matching crates with names, versions, descriptions, download counts, and URLs. After finding a crate, use: - crates_metadata() to get detailed information about a specific crate - The documentation URL to read full docs (use WebFetch) Args: query: Search keywords (e.g., "http client", "web framework", "serde") limit: Maximum number of results (default 5, max 100) Returns: JSON with list of matching crates, total results, and metadata Example: search_crates("web framework") → Finds actix-web, rocket, axum, etc. """ result = await self._search_crates(query, per_page=limit) return serialize_response_with_meta(result)
• src/RTFD/providers/crates.py:77-126 (helper)

  Internal helper method that performs the actual HTTP request to crates.io API, handles rate limiting, parses and formats the search results.
  async def _search_crates(self, query: str, per_page: int = 5) -> dict[str, Any]: """Search for crates by name/keyword.""" await self._rate_limit() try: async with await self._http_client() as client: response = await client.get( f"{self.BASE_URL}/crates", params={"q": query, "per_page": min(per_page, 100), "page": 1}, ) response.raise_for_status() data = response.json() # Format the response crates = data.get("crates", []) formatted_crates = [] for crate in crates[:per_page]: formatted_crates.append( { "name": crate.get("name"), "version": crate.get("max_version"), "description": crate.get("description", ""), "downloads": crate.get("downloads"), "recent_downloads": crate.get("recent_downloads"), "repository": crate.get("repository"), "documentation": crate.get("documentation"), "homepage": crate.get("homepage"), "license": crate.get("license"), "categories": crate.get("categories", []), "keywords": crate.get("keywords", []), "created_at": crate.get("created_at"), "updated_at": crate.get("updated_at"), } ) return { "query": query, "results": formatted_crates, "total": data.get("meta", {}).get("total"), "source": "https://crates.io/", } except Exception as e: return { "query": query, "error": str(e), "source": "https://crates.io/", }
• src/RTFD/providers/crates.py:166-222 (registration)

  The get_tools method registers the search_crates tool by defining it and including it in the returned dictionary of MCP tools.
  def get_tools(self) -> dict[str, Callable]: """Return MCP tool functions.""" async def search_crates(query: str, limit: int = 5) -> CallToolResult: """ Search for Rust crates on crates.io by name or keywords. USE THIS WHEN: You need to find Rust packages/crates for a specific purpose or library. BEST FOR: Discovering which Rust crates exist for a topic or functionality. Returns multiple matching crates with names, versions, descriptions, download counts, and URLs. After finding a crate, use: - crates_metadata() to get detailed information about a specific crate - The documentation URL to read full docs (use WebFetch) Args: query: Search keywords (e.g., "http client", "web framework", "serde") limit: Maximum number of results (default 5, max 100) Returns: JSON with list of matching crates, total results, and metadata Example: search_crates("web framework") → Finds actix-web, rocket, axum, etc. """ result = await self._search_crates(query, per_page=limit) return serialize_response_with_meta(result) async def crates_metadata(crate: str) -> CallToolResult: """ Get detailed metadata for a specific Rust crate from crates.io. USE THIS WHEN: You need comprehensive information about a specific Rust crate. RETURNS: Detailed crate metadata including version, URLs, downloads, and license. Does NOT include full documentation content. The response includes: - Crate name, version, description - Documentation URL (docs.rs) - can be passed to WebFetch for full API docs - Repository URL (usually GitHub) - can be used with GitHub provider - Homepage, license, categories, keywords - Download statistics, creation/update dates - Minimum Rust version required Args: crate: Crate name (e.g., "serde", "tokio", "actix-web") Returns: JSON with comprehensive crate metadata Example: crates_metadata("serde") → Returns metadata with docs.rs link and GitHub repo """ result = await self._get_crate_metadata(crate) return serialize_response_with_meta(result) return {"search_crates": search_crates, "crates_metadata": crates_metadata}
• src/RTFD/providers/crates.py:30-39 (registration)

  Provider metadata that lists 'search_crates' as one of the exposed tool names.
  def get_metadata(self) -> ProviderMetadata: return ProviderMetadata( name="crates", description="Rust crates.io package registry metadata", expose_as_tool=True, tool_names=["crates_metadata", "search_crates"], supports_library_search=True, required_env_vars=[], optional_env_vars=[], )