Docs MCP Server
A TypeScript-based Model Context Protocol (MCP) server for serving Tambo documentation from https://docs.tambo.co/
Features
- Dynamic Documentation Discovery: Automatically crawls and discovers all available documentation pages
- Intelligent Content Parsing: Extracts clean content from Fumadocs-powered sites
- Fast Search: Search across all discovered documentation
- TypeScript: Full type safety and modern development experience
- Caching: 10-minute cache for improved performance
Installation
Usage
Development (with hot reload)
Production
Testing
Available Tools
- discover_docs: Crawl and discover all available documentation paths automatically
- fetch_docs: Fetch specific documentation pages by path
- search_docs: Search documentation for specific terms across all discovered pages
- list_sections: List all discovered documentation sections, grouped by category
Installation
In Cursor
Create or update .cursor/mcp.json
in your project root:
MacOS/Linux:
Windows:
Note: The MCP server won't be enabled by default. Go to Cursor settings → MCP settings and click "enable" on the Tambo Docs MCP server.
In Claude Desktop
Update your Claude Desktop configuration:
MacOS/Linux: ~/.claude/config.json
Windows: %APPDATA%\Claude\config.json
In Windsurf
Create or update ~/.codeium/windsurf/mcp_config.json
:
MacOS/Linux:
Windows:
Setup
Before using, build the server:
Development
The server is built with TypeScript and uses:
- @modelcontextprotocol/sdk: MCP protocol implementation
- cheerio: HTML parsing and content extraction
- tsx: Fast TypeScript execution for development
hybrid server
The server is able to function both locally and remotely, depending on the configuration or use case.
Enables AI assistants to discover, fetch, and search through Tambo documentation from docs.tambo.co. Provides intelligent content parsing with caching for improved performance when accessing technical documentation.
Related MCP Servers
- -securityAlicense-qualityAccess any documentation indexed by RagRabbit Open Source AI site searchLast updated -2115TypeScriptMIT License
- -securityAlicense-qualityProvides tools for retrieving and processing documentation through vector search, enabling AI assistants to augment their responses with relevant documentation context.Last updated -9TypeScriptMIT License
- -securityFlicense-qualityEnables AI assistants to search documentation of packages and services to find implementation details, examples, and specifications.Last updated -Python
- -securityFlicense-qualityEnables AI assistants to search for documentation of packages and services, providing implementation details, examples, and specifications through a specialized API.Last updated -92JavaScript