Node.js API Documentation MCP Server
Enables querying Node.js API documentation, including searching for modules and listing all available modules with their methods.
README
MCP Server for Node.js API Documentation
This project implements a Model Context Protocol (MCP) server that provides access to the official Node.js API documentation. It fetches the documentation from nodejs.org and exposes it through MCP tools.
Features
- Fetches the latest Node.js API documentation.
- Provides MCP tools to query documentation for specific modules, classes, or methods.
- Offers a search tool (
node-search) to find modules or list all available modules with their methods. - Offers a list tool (
node-list) to get a summary of all available modules. - Logs activity and errors to
/tmp/mcp-server-nodejs-docs.logusingpino.
Installation
- Clone the repository (if applicable):
git clone <repository_url> cd <repository_directory> - Install dependencies:
This project requires Node.js and npm.
npm install
Usage
To start the MCP server, run the following command in your terminal:
npm run start
The server will initialize, fetch the documentation, create the necessary tools, and then listen for connections over standard input/output (stdio).
To enable debug logging, start the server with the --debug flag:
node index.js --debug
Debugging
The server logs detailed information about its operations, including fetches, tool executions, and errors, to the following file:
/tmp/mcp-server-nodejs-docs.log
You can monitor this file to debug issues:
tail -f /tmp/mcp-server-nodejs-docs.log
Testing with MCP Inspector
Use the built-in debug script:
npm run debug
Or directly via npx:
npx -y @modelcontextprotocol/inspector node index.js
Connecting to MCP Clients
This server communicates over standard input/output (stdio). To connect it to MCP clients like Cursor or Qodo AI, you need to configure the client to launch the server using its command.
Example Configuration (Conceptual):
Most clients will have a settings area where you can add custom MCP servers. You'll typically need to provide:
-
A Name: e.g., "Node.js API Documentation"
-
The Command: The command to execute the server. Make sure to provide the absolute path to
nodeand theindex.jsfile, or ensurenodeis in the PATH environment variable accessible by the client.# Example - replace with your actual absolute paths /path/to/your/node /path/to/your/project/index.js- Finding Node Path: Run
which nodein your terminal. - Finding Project Path: Navigate to the project directory and run
pwd.
- Finding Node Path: Run
Refer to your specific MCP client's documentation for the exact steps on adding a stdio-based server.
Example using Cursor:
- Go to
Settings->Cursor Settings->MCP Servers. - Click
Add Server. - Enter a name (e.g., "NodeJS API Documentation").
- In the
Commandfield, enter the full command, like:/Users/youruser/.nvm/versions/node/v20.11.1/bin/node /Users/youruser/projects/mcp-server-nodejs-docs/index.js(replace paths with your actual paths). - Save the server configuration.
- You should now be able to use the
@NodeJS API Documentationtag (or whatever name you chose) in your chat prompts.
Author
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.