GitHub MCP Server
MCP server for accessing GitHub documentation via API, allowing users to fetch repositories, documentation files, and search across documentation with base64 decoding support.
README
title: GitHub MCP Server emoji: 🐙 colorFrom: blue colorTo: purple sdk: docker app_port: 7860
GitHub MCP Server
Model Context Protocol server for accessing GitHub documentation via API.
Features
- Fetch repositories from organizations with
/docfolder detection - Access documentation files from repositories
- Search across documentation
- Automatic base64 decoding
- MCP-compliant tools and resources
Quick Start (Docker)
1. Pull the image
docker pull ghcr.io/sperekrestova/github-mcp-server:latest
2. Configure Claude Desktop
Add to claude_desktop_config.json:
macOS: ~/Library/Application Support/Claude/claude_desktop_config.json
Windows: %APPDATA%\Claude\claude_desktop_config.json
Linux: ~/.config/Claude/claude_desktop_config.json
{
"mcpServers": {
"github-docs": {
"command": "docker",
"args": [
"run",
"-i",
"--rm",
"-e", "GITHUB_TOKEN",
"ghcr.io/sperekrestova/github-mcp-server:latest"
],
"env": {
"GITHUB_TOKEN": "ghp_your_token_here"
},
"autoapprove": [
"get_org_repos_tool",
"get_repo_docs_tool",
"get_file_content_tool",
"search_documentation_tool"
]
}
}
}
3. Get GitHub Token
- Go to https://github.com/settings/tokens
- Generate new token (classic)
- Required scopes:
repo,read:org,read:user - Add token to configuration above
4. Restart Claude Desktop
Ask Claude:
- "What documentation exists in the anthropics organization?"
- "Show me docs from the anthropic-sdk-python repository"
- "Search for streaming examples in anthropics repos"
MCP Tools
- get_org_repos(org) - List repositories with /doc folder detection
- get_repo_docs(org, repo) - Get documentation files from repository
- get_file_content(org, repo, path) - Fetch file content with base64 decoding
- search_documentation(org, query) - Search documentation across repositories
MCP Resources
documentation://{org}/{repo}- List documentation filescontent://{org}/{repo}/{path}- Get file content
Building from Source
Local Docker build:
# Enable BuildKit for faster builds
export DOCKER_BUILDKIT=1
# Build (~30 seconds with cache)
docker build -t github-mcp-server:local .
# Or use docker-compose
docker-compose build
Python setup (for development):
python3 -m venv venv
source venv/bin/activate
pip install -r requirements.txt
cp .env.example .env
# Add GITHUB_TOKEN to .env
python main.py
Claude Desktop config (Python):
{
"mcpServers": {
"github-docs": {
"command": "python3",
"args": ["/absolute/path/to/main.py"],
"env": {
"GITHUB_TOKEN": "ghp_your_token_here"
},
"autoapprove": ["get_org_repos_tool", "get_repo_docs_tool", "get_file_content_tool", "search_documentation_tool"]
}
}
}
Environment Variables
GITHUB_TOKEN- GitHub personal access token (required)GITHUB_API_BASE_URL- GitHub API URL (default: https://api.github.com)LOG_LEVEL- Logging level (default: INFO)
Supported File Types
Markdown (.md), Mermaid (.mmd, .mermaid), SVG (.svg), OpenAPI (.yml, .yaml, .json), Postman collections (.json)
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.