GitHub MCP Server
Enables AI agents to interact with GitHub, providing tools to list and get repository details using a personal access token.
README
MCP Servers Monorepo
This repository is a monorepo for Model Context Protocol (MCP) servers, using pnpm workspaces. It currently contains the GitHub MCP Server, which provides tools to interact with GitHub using an AI agent.
Setup
-
Install Dependencies Run the following command at the root of the repository to install all required dependencies:
pnpm install -
Configure Environment Variables The GitHub MCP server requires a Personal Access Token (PAT) to interact with the GitHub API.
Navigate to the GitHub app directory and create your
.envfile:cd apps/github-mcp cp .env.example .envOpen the
.envfile and replaceyour_personal_access_token_herewith your actual GitHub PAT. You can generate one from your GitHub Developer Settings. Make sure it hasrepoaccess.
Running the Server
You can run the server directly (it will run on stdio and wait for JSON-RPC messages):
pnpm run dev
(Note: Running this command directly won't give you interactive feedback, as it's designed to be consumed by an AI client.)
Debugging and Testing (MCP Inspector)
To test the MCP tools interactively, you can use the official MCP Inspector. We have set up a convenient script that runs the inspector without polluting the standard output with pnpm logs.
From the root of the repository, run:
pnpm run inspector
How to use the Inspector:
- The command will output a local URL (e.g.,
http://localhost:5173). - Open that URL in your browser.
- Click the Connect button in the top right corner.
- You will see a list of tools (like
listRepositories,getRepository, etc.). - Click on a tool, enter the arguments (e.g.,
nilesh-singh-mefor theownerfield), and click Run Tool to see the live data fetched from GitHub!
Project Structure
apps/github-mcp/: The GitHub MCP server implementation.src/tools/: Contains individual files for each tool (schemas and handlers).src/index.ts: The main entrypoint that registers the tools and starts the server.src/config.ts: Configuration loader (handles.env).src/github.ts: The Octokit GitHub client setup.
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.