github-mcp-server
A minimal MCP server for GitHub that enables browsing repos, reading code, searching, and getting insights through natural language via Claude, Cursor, or any MCP client.
README
github-mcp-server
A minimal MCP server for GitHub in ~140 lines of Python. Browse repos, read code, search, and get insights — all through natural language via Claude, Cursor, or any MCP client.
Tools
| Tool | Description |
|---|---|
list_repos |
List repositories with language, stars, and last update |
get_repo_structure |
View the file tree of any repo |
get_file |
Read any file's content |
search_code |
Search code across your repos |
list_issues |
Get open/closed issues |
get_commits |
Recent commit history |
repo_stats |
Languages breakdown, stars, forks, dates |
Quick Start
# Clone
git clone https://github.com/ArnabbLank/github-mcp-server.git
cd github-mcp-server
# Install
pip install -e .
# Configure
cp .env.example .env
# Edit .env with your GitHub token (Settings → Developer settings → Personal access tokens)
# Run
mcp dev server.py
Connect to Claude Desktop
Add to ~/Library/Application Support/Claude/claude_desktop_config.json:
{
"mcpServers": {
"github": {
"command": "python",
"args": ["/path/to/github-mcp-server/server.py"],
"env": {
"GITHUB_TOKEN": "ghp_your_token",
"GITHUB_OWNER": "your_username"
}
}
}
}
Restart Claude Desktop. You can now ask things like:
- "Show me my recent repos"
- "Read the README from my EnvCraft project"
- "Search for uses of FastAPI across my repos"
- "What issues are open on github-mcp-server?"
How It Works
This server implements the Model Context Protocol using fastmcp. Each tool is a Python function decorated with @mcp.tool() — the MCP client (Claude, Cursor) discovers them automatically and calls them when relevant.
┌─────────────┐ MCP (stdio/SSE) ┌──────────────┐ HTTPS ┌────────┐
│ Claude/Cursor│ ◄──────────────────────────► │ server.py │ ◄──────────────► │ GitHub │
│ (MCP Client)│ │ (MCP Server) │ │ API │
└─────────────┘ └──────────────┘ └────────┘
Add Your Own Tool
@mcp.tool()
async def my_tool(repo: str, owner: str = "") -> str:
"""Description shown to the LLM."""
owner = owner or OWNER
data = await _get(f"/repos/{owner}/{repo}/whatever")
return format_data(data)
That's it. The LLM sees the function name, docstring, and parameter types — no extra config needed.
Token Permissions
The GitHub token needs these scopes:
repo— for private repo access (optional, skip for public-only)read:user— for listing repos
Generate one at: https://github.com/settings/tokens
License
MIT
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.