- Home
- MCP servers
- Docs
Docs
- typescript
1
GitHub Stars
typescript
Language
6 months ago
First Indexed
2 months ago
Catalog Refreshed
Documentation & install
Readme and setup notes from the catalogue, plus a client-ready config you can copy for your MCP host.
Installation
Add the following to your MCP client configuration file.
Configuration
View docs{
"mcpServers": {
"kylegrahammatzen-tambo-mcp-server": {
"command": "node",
"args": [
"D:/oss/docs-mcp-server/dist/index.js"
]
}
}
}You can run a dedicated MCP server that serves Tambo documentation, enabling dynamic discovery, fast search, and clean content extraction for your documentation needs. This server is built with TypeScript, provides type safety, and caches results for improved performance, making it ideal for integrating documentation access into your workflow.
How to use
You will connect an MCP client to the server to access and search documentation pages. The server automatically discovers available documentation, parses content from Fumadocs-powered sites, and exposes search across all discovered pages. Use the client to request specific pages, list sections, or perform broad searches across the documentation corpus.
How to install
Prerequisites: You need Node.js installed on your system. Ensure npm is available as it is used to install and run the server.
Step by step commands to set up the MCP server locally:
npm install
npm run build
npm start
Configuration and usage notes
To enable the MCP server for use in clients, locate the configuration area in your tooling environment and enable the Tambo Docs MCP server. This server supports multiple integration points, including local development and production deployment, with a focus on reliable access to documentation content.
The server relies on TypeScript tooling and common npm-based workflows. You can run development builds with hot reload using the development command, or build for production and start the server to serve content to MCP clients.
Notes and troubleshooting
If you encounter issues with discovery or content parsing, verify that the server has network access to the documentation sources and that the parsing components are functioning correctly. The 10-minute caching helps performance, but if you need fresh results, you can restart the server to refresh the cache.
What you can do with the server
- Automatically crawl and discover all documentation paths
- Parse and clean content from supported sites
- Search across all discovered documentation
- List sections grouped by category
- Provide fast, typed access for client integrations
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.