GitHub Tools MCP Server
Enables read-only interaction with GitHub through the REST API via natural language, allowing users to query GitHub data from Claude Desktop or Claude Code.
README
GitHub Tools MCP Server
A real Model Context Protocol server exposing read-only tools against the GitHub REST API — installable into Claude Desktop or Claude Code in under a minute — plus a separate web demo exercising the same tool logic through an ordinary chat UI.
Live demo: https://mcp-demo-phi.vercel.app/demo
Status: what this is and isn't
Working and deployed. All 5 tools verified against real GitHub data,
42 automated checks across 3 test suites, and the full app confirmed live
on the real production URL. See DESIGN_LOG.md for the
running, honest account of every decision and bug along the way.
The web demo is NOT an MCP transport. It's plain FastAPI calling the
same tools.py functions directly as Python, not speaking the MCP protocol.
Genuinely useful distinction to be precise about — see DESIGN_LOG.md
section 3 for why a real remote MCP transport isn't attempted here.
Architecture
┌─────────────────────┐
│ tools.py │ <- 5 pure functions, no
│ (GitHub REST calls │ MCP-specific code
│ via github_client) │
└──────────┬───────────┘
│
┌────────────────┴────────────────┐
│ │
┌─────────▼─────────┐ ┌───────────▼──────────┐
│ server.py │ │ api/index.py │
│ MCPServer, stdio │ │ FastAPI, POST /chat │
│ transport │ │ real Claude tool- │
│ -> Claude Desktop/ │ │ calling loop over │
│ Claude Code │ │ the same tools │
└─────────────────────┘ └────────────────────────┘
THE MCP SERVER A PLAIN HTTP DEMO OF
(the real deliverable) THE SAME TOOL LOGIC
Setup
cp .env.example .env # GITHUB_TOKEN (both halves), ANTHROPIC_API_KEY (web demo only)
pip install -r requirements.txt
Run the MCP server locally
python3 server.py
Add to Claude Desktop: edit
%APPDATA%\Claude\claude_desktop_config.json (Windows) /
~/Library/Application Support/Claude/claude_desktop_config.json (macOS),
merging in the contents of claude_desktop_config.example.json (fill in
your real GITHUB_TOKEN and the absolute path to server.py), then
restart Claude Desktop. Add to Claude Code: claude mcp add or edit
your project's .mcp.json the same way.
Manual interactive dev workflow: the SDK ships an inspector for poking at
the server by hand without a full client —
npx @modelcontextprotocol/inspector python3 server.py.
Run the web demo locally
export $(cat .env | xargs)
uvicorn api.index:app --reload --port 8020
Design log
Every non-obvious decision, plus the SDK API surface verified against the
actually-installed package rather than assumed from possibly-stale docs, is
in DESIGN_LOG.md.
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.
Neon Database
MCP server for interacting with Neon Management API and databases
E2B
Using MCP to run code via e2b.
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.