github-graphql
MCP server from QuentinCody/github-graphql-mcp-server
claude mcp add --transport stdio quentincody-github-graphql-mcp-server python github_graphql_mcp_server.py \ --env GITHUB_TOKEN="your_github_token_here"
How to use
This MCP server exposes a single tool that lets you execute arbitrary GraphQL queries and mutations against GitHub's GraphQL API. After starting the server with a valid GitHub token, you can issue GraphQL operations through the MCP interface by calling the github-graphql tool. It supports standard GraphQL features such as variables, fragments, and inline arguments, and it returns structured results along with error information when applicable. Use cases include fetching repository data, user details, and performing searches, all within the GitHub GraphQL schema.
To use the tool, ensure your environment provides the GITHUB_TOKEN as an environment variable. When you query, provide your GraphQL query string and, if needed, a variables object in the request payload. The server handles authentication, error reporting, and response formatting, so you can focus on crafting valid GraphQL operations and interpreting the results.
How to install
Prerequisites:
- Python 3.10 or higher
- Git and access to the repository
- A GitHub Personal Access Token (PAT) with appropriate scopes
Installation steps:
- Clone the repository git clone https://github.com/quentincody/github-graphql-mcp-server.git
- Create and activate a virtual environment (recommended)
macOS/Linux
python3 -m venv .venv source .venv/bin/activateWindows
python -m venv .venv\Scripts\activate - Install dependencies pip install -r requirements.txt
- Run the server (provide your GitHub token via environment variable) GITHUB_TOKEN=your_github_token_here python github_graphql_mcp_server.py
If you plan to integrate with Claude Desktop, configure the corresponding entry to point to the Python interpreter inside your virtual environment and the path to github_graphql_mcp_server.py, as shown in the README:
Additional notes
Tips and common issues:
- Ensure your GITHUB_TOKEN has the necessary permissions for the operations you want to perform.
- Activate your virtual environment before launching the server to guarantee Python dependencies are available.
- Use absolute paths when configuring Claude Desktop integrations to avoid path resolution issues.
- Check server logs for error messages if queries fail or tokens are not recognized.
- GitHub API rate limits apply; authenticated requests have higher limits than unauthenticated requests.
Related MCP Servers
mcp-vegalite
MCP server from isaacwasserman/mcp-vegalite-server
github-chat
A Model Context Protocol (MCP) for analyzing and querying GitHub repositories using the GitHub Chat API.
nautex
MCP server for guiding Coding Agents via end-to-end requirements to implementation plan pipeline
pagerduty
PagerDuty's official local MCP (Model Context Protocol) server which provides tools to interact with your PagerDuty account directly from your MCP-enabled client.
futu-stock
mcp server for futuniuniu stock
mcp -boilerplate
Boilerplate using one of the 'better' ways to build MCP Servers. Written using FastMCP