GitHub GraphQL API MCP server for AI agents

The GitHub GraphQL API MCP server provides a powerful interface to the GitHub GraphQL API through the Model Control Protocol, making it easier to query GitHub data with precise control over what information you retrieve.

Installation

Prerequisites

Python 3.10 or higher
GitHub personal access token
Poetry (recommended for dependency management)

Setup Instructions

Clone the repository:

git clone https://github.com/wanzunz/github_graphql_api_mcp.git
cd github_graphql_api_mcp

Install dependencies:

Using Poetry (recommended):

# Install Poetry if needed
# curl -sSL https://install.python-poetry.org | python3 -

# Install dependencies
poetry install

# Activate virtual environment
poetry shell

Without Poetry:

# Create and activate virtual environment
python -m venv .venv
source .venv/bin/activate  # Linux/MacOS
# or
.venv\Scripts\activate  # Windows

# Install dependencies
pip install -e .

Configure your GitHub token:

Create a .env file with your GitHub personal access token:

cp .env.example .env

Then edit the .env file to add your token:

GITHUB_TOKEN="your_github_token_here"

Starting the Server

After activating your virtual environment:

python github_graphql_api_mcp_server.py

Claude Desktop Configuration

You can configure the Claude desktop app to start the MCP server with one click:

Open Claude desktop app
Go to settings and find the MCP server configuration section
Add the following configuration (adjust paths as needed):

{
    "mcpServers": {
        "github_mcp": {
            "command": "/usr/bin/python3",
            "args": [
                "--directory",
                "/home/user/projects/github_graphql_api_mcp/",
                "run",
                "github_graphql_api_mcp_server.py"
            ]
        }
    }
}

For conda or other environment management tools:

{
    "mcpServers": {
        "github_mcp": {
            "command": "/opt/miniconda3/bin/python",
            "args": [
                "--directory",
                "/Users/username/github/github_graphql_api_mcp/",
                "run",
                "github_graphql_api_mcp_server.py"
            ]
        }
    }
}

Using the MCP Server

Available Tools

The server provides four main tools:

print_type_field: Query fields of GitHub GraphQL schema root types
graphql_schema_root_type: Get documentation for root types (Query/Mutation)
graphql_schema_type: Query documentation for specific types
call_github_graphql: Execute GitHub GraphQL API queries

Usage Examples

Once connected to the server with an MCP client (like Claude), you can use the tools as follows:

1. Query root type documentation

Use the graphql_schema_root_type tool, parameter type_name="QUERY"

2. Query fields of specific types

Use the print_type_field tool, parameters type_name="QUERY", type_fields_name="repository"

3. Query documentation for specific types

Use the graphql_schema_type tool, parameter type_name="Repository"

4. Execute GraphQL queries

Use the call_github_graphql tool, parameter:
graphql="""
query {
  viewer {
    login
    name
  }
}
"""

Common Use Cases

This server is particularly useful for:

Repository information: Query repository name, description, star count, branch list
Issue data retrieval: Access issue lists, details, and comments
User profile information: Retrieve user profiles and contribution statistics
Pull request status: Get PR status, comments, and merge information
Project dependencies: Query project dependency packages and versions

Advanced Usage

With GraphQL's flexibility, you can build more complex queries for:

Repository contribution trend analysis
Issue management and classification
Code review pattern analysis
Contributor network visualization
Dependency health assessment

Remember that your queries should comply with GitHub API usage limits, and ensure your token has the appropriate permissions for the data you're trying to access.

How to install this MCP server

For Claude Code

To add this MCP server to Claude Code, run this command in your terminal:

claude mcp add-json "github_mcp" '{"command":"/usr/bin/python3","args":["--directory","/home/user/projects/github_graphql_api_mcp/","run","github_graphql_api_mcp_server.py"]}'

See the official Claude Code MCP documentation for more details.

For Cursor

There are two ways to add an MCP server to Cursor. The most common way is to add the server globally in the ~/.cursor/mcp.json file so that it is available in all of your projects.

If you only need the server in a single project, you can add it to the project instead by creating or adding it to the .cursor/mcp.json file.

Adding an MCP server to Cursor globally

To add a global MCP server go to Cursor Settings > Tools & Integrations and click "New MCP Server".

When you click that button the ~/.cursor/mcp.json file will be opened and you can add your server like this:

{
    "mcpServers": {
        "github_mcp": {
            "command": "/usr/bin/python3",
            "args": [
                "--directory",
                "/home/user/projects/github_graphql_api_mcp/",
                "run",
                "github_graphql_api_mcp_server.py"
            ]
        }
    }
}

Adding an MCP server to a project

To add an MCP server to a project you can create a new .cursor/mcp.json file or add it to the existing one. This will look exactly the same as the global MCP server example above.

How to use the MCP server

Once the server is installed, you might need to head back to Settings > MCP and click the refresh button.

The Cursor agent will then be able to see the available tools the added MCP server has available and will call them when it needs to.

You can also explicitly ask the agent to use the tool by mentioning the tool name and describing what the function does.

For Claude Desktop

To add this MCP server to Claude Desktop:

1. Find your configuration file:

macOS: ~/Library/Application Support/Claude/claude_desktop_config.json
Windows: %APPDATA%\Claude\claude_desktop_config.json
Linux: ~/.config/Claude/claude_desktop_config.json

2. Add this to your configuration file:

{
    "mcpServers": {
        "github_mcp": {
            "command": "/usr/bin/python3",
            "args": [
                "--directory",
                "/home/user/projects/github_graphql_api_mcp/",
                "run",
                "github_graphql_api_mcp_server.py"
            ]
        }
    }
}

3. Restart Claude Desktop for the changes to take effect