Skip to main content
Glama

gh-mcp

README.md1.64 kB
# `gh-mcp` Refined MCP server for GitHub GraphQL API. > [!TIP] > If you haven't read the article [The second wave of MCP: Building for LLMs, not developers](https://vercel.com/blog/the-second-wave-of-mcp-building-for-llms-not-developers) by Vercel, I highly recommend checking it out to understand why we're building this project. [GitHub's official MCP Server](https://github.com/github/github-mcp-server) exposes dozens of low-level tools that bloat token usage and are mostly impractical for LLMs. `gh-mcp` achieves the best of both worlds by providing a single, powerful interface: GitHub GraphQL, wrapped with smart abstractions. This project does 3 things differently: 1. **One powerful tool** — exposes GraphQL instead of atomized endpoints. LLMs already understand GraphQL. 2. **YAML output by default** — makes nested data and file content readable without escaping. 3. **Clean abstractions** — handles authentication and low-level details. LLMs know how to use `--jq` to filter. Swapping in `gh-mcp` delivers better performance at lower cost for any GitHub interactions. ## Installation with uv: ```sh uvx mcp-hmr ``` MCP config: ```json { "mcpServers": { "gh": { "command": "uvx", "args": ["gh-mcp"] } } } ``` If you prefer serving it via streamable-http: ```sh uvx gh-mcp --http ``` > [!NOTE] > This project requires `gh` CLI to be installed and authenticated. Please follow the instructions at [cli.github.com](https://cli.github.com/) to set it up. And then you can login via `gh auth login`. Check that `gh auth status` works before using this MCP server.

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/CNSeniorious000/gh-mcp'

If you have feedback or need assistance with the MCP directory API, please join our Discord server