Skip to main content
Glama
GitHub Activity MCP Server

GitHub Activity MCP Server

šŸš€ GitHub Activity MCP Server

An MCP (Model Context Protocol) server built with FastMCP and PyGithub that connects AI assistants to GitHub — search repos, manage issues & PRs, analyze contributions, and more.

What is MCP? The Model Context Protocol is an open standard that lets AI assistants connect to external data and tools through a unified interface. Think of it as "USB-C for AI".


✨ Features

This server exposes 13 tools, 3 resource providers, and 3 prompt templates — covering all three MCP primitives.

šŸ”§ Tools (Model-Controlled)

Actions the AI can take autonomously:

Tool

Description

search_repositories

Search GitHub repos by query, language, stars

get_repository

Get detailed repo info (stars, forks, topics, etc.)

get_file_contents

Read any file from a repo

list_commits

List recent commits with filters

list_issues

List issues with state/label/assignee filters

get_issue

Get full issue details + comments

create_issue

Create a new issue

add_issue_comment

Comment on an issue

list_pull_requests

List PRs with state/branch filters

get_pull_request

Get PR details + merge status

get_pull_request_diff

View PR code changes

get_user_profile

Get a user's public profile

list_user_repos

List a user's repositories

šŸ“¦ Resources (Application-Controlled)

Contextual data the AI can read:

Resource URI

Description

github://repo/{owner}/{repo}/readme

Repository README (markdown)

github://repo/{owner}/{repo}/tree

Full file tree listing

github://repo/{owner}/{repo}/languages

Language breakdown with percentages

šŸ’¬ Prompts (User-Triggered)

Pre-built workflow templates:

Prompt

Description

analyze-repo

Comprehensive repository analysis

review-pr

Code review with best practices

issue-triage

Categorize and prioritize open issues


Related MCP server: GitHub MCP Server

šŸ—ļø Architecture

graph LR
    A[AI Assistant] <-->|MCP Protocol| B[GitHub MCP Server]
    B <-->|REST API| C[GitHub API]

    subgraph "MCP Server (FastMCP)"
        B --> D[Tools]
        B --> E[Resources]
        B --> F[Prompts]
    end

    subgraph "Tools"
        D --> D1[Repos]
        D --> D2[Issues]
        D --> D3[Pull Requests]
        D --> D4[Users]
    end

šŸš€ Quick Start

Prerequisites

  • Python ≄ 3.10

  • GitHub Personal Access Token (optional, but recommended for higher rate limits)

Installation

# Clone the repository
git clone https://github.com/YOUR_USERNAME/github-mcp-server.git
cd github-mcp-server

# Install dependencies
pip install fastmcp PyGithub

Set up your GitHub Token (Optional)

Create a Personal Access Token with repo and read:user scopes:

# Linux/macOS
export GITHUB_TOKEN=ghp_your_token_here

# Windows (PowerShell)
$env:GITHUB_TOKEN = "ghp_your_token_here"

Note: Without a token, you're limited to 60 API requests/hour. With a token, you get 5,000/hour.

Run the Server

# Run directly
fastmcp run src/server.py

# Or with Python
python -m src.server

Test with FastMCP Dev Mode

fastmcp dev src/server.py

āš™ļø Configuration

Claude Desktop

Add to your Claude Desktop config (~/Library/Application Support/Claude/claude_desktop_config.json on macOS, or %APPDATA%\Claude\claude_desktop_config.json on Windows):

{
  "mcpServers": {
    "github": {
      "command": "fastmcp",
      "args": ["run", "src/server.py"],
      "cwd": "/absolute/path/to/github-mcp-server",
      "env": {
        "GITHUB_TOKEN": "ghp_your_token_here"
      }
    }
  }
}

Cursor

Add to your Cursor MCP config (.cursor/mcp.json in your project or global config):

{
  "mcpServers": {
    "github": {
      "command": "fastmcp",
      "args": ["run", "src/server.py"],
      "cwd": "/absolute/path/to/github-mcp-server",
      "env": {
        "GITHUB_TOKEN": "ghp_your_token_here"
      }
    }
  }
}

VS Code (GitHub Copilot)

Add to your VS Code settings (.vscode/settings.json):

{
  "mcp": {
    "servers": {
      "github": {
        "command": "fastmcp",
        "args": ["run", "src/server.py"],
        "cwd": "/absolute/path/to/github-mcp-server",
        "env": {
          "GITHUB_TOKEN": "ghp_your_token_here"
        }
      }
    }
  }
}

šŸ“ Project Structure

github-mcp-server/
ā”œā”€ā”€ src/
│   ā”œā”€ā”€ __init__.py
│   ā”œā”€ā”€ server.py             # FastMCP server instance & entry point
│   ā”œā”€ā”€ github_client.py      # PyGithub client wrapper & error handling
│   ā”œā”€ā”€ resources.py          # Resource providers (README, tree, languages)
│   ā”œā”€ā”€ prompts.py            # Prompt templates (analyze, review, triage)
│   └── tools/
│       ā”œā”€ā”€ __init__.py
│       ā”œā”€ā”€ repos.py          # Repository tools (search, get, file contents, commits)
│       ā”œā”€ā”€ issues.py         # Issue tools (list, get, create, comment)
│       ā”œā”€ā”€ pulls.py          # Pull request tools (list, get, diff)
│       └── users.py          # User tools (profile, repos)
ā”œā”€ā”€ pyproject.toml
ā”œā”€ā”€ README.md
ā”œā”€ā”€ LICENSE
└── .gitignore

šŸ› ļø Tech Stack

Technology

Purpose

FastMCP

High-level MCP server framework

PyGithub

GitHub REST API client

Model Context Protocol

The open standard for AI-tool integration


šŸ¤ Contributing

Contributions are welcome! Here's how:

  1. Fork the repository

  2. Create a feature branch (git checkout -b feature/amazing-feature)

  3. Commit your changes (git commit -m 'Add amazing feature')

  4. Push to the branch (git push origin feature/amazing-feature)

  5. Open a Pull Request


šŸ“„ License

This project is licensed under the MIT License — see the LICENSE file for details.


Available Tools

13 tools
add_issue_commentB

Add a comment to an existing GitHub issue.

Inputs: body (required), repo (required), owner (required), issue_number (required). Returns: result

create_issueB

Create a new issue in a GitHub repository.

Inputs: repo (required), owner (required), title (required), body, +2 more. Returns: result

get_file_contentsB

Read the contents of a file from a GitHub repository.

Inputs: path (required), repo (required), owner (required), ref. Returns: result

get_issueA

Get detailed information about a specific issue, including its comments.

Inputs: repo (required), owner (required), issue_number (required). Returns: result

get_pull_requestC

Get detailed information about a specific pull request.

Inputs: repo (required), owner (required), pull_number (required). Returns: result

get_pull_request_diffB

Get the diff/patch of a pull request to review code changes.

Inputs: repo (required), owner (required), pull_number (required). Returns: result

get_repositoryA

Get detailed information about a specific GitHub repository.

Inputs: repo (required), owner (required). Returns: result

get_user_profileA

Get public profile information for a GitHub user.

Inputs: username (required). Returns: result

list_commitsA

List recent commits for a repository, optionally filtered by path or author.

Inputs: repo (required), owner (required), sha, path, +2 more. Returns: result

list_issuesB

List issues in a GitHub repository with optional filters.

Inputs: repo (required), owner (required), sort, state, +3 more. Returns: result

list_pull_requestsC

List pull requests in a GitHub repository.

Inputs: repo (required), owner (required), base, sort, +3 more. Returns: result

list_user_reposB

List repositories for a GitHub user.

Inputs: username (required), sort, per_page. Returns: result

search_repositoriesB

Search GitHub repositories by query. Supports GitHub search qualifiers.

Inputs: query (required), sort, order, language, +1 more. Returns: result

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

Loading tool schema changelog…

    TDQS

    A3.6/5.0

    Scored across 13 tools

    Disambiguation5/5

    Each tool targets a distinct resource and action: repositories, files, commits, issues, pull requests, and user profiles are cleanly separated. There is no meaningful overlap between tools like get_repository and search_repositories or list_issues and get_issue.

    Naming Consistency5/5

    All tool names follow a consistent snake_case verb_noun pattern, such as search_repositories, get_file_contents, and create_issue. Minor semantic differences between verbs like get and list are still predictable and uniform across the set.

    Tool Count5/5

    Thirteen tools is well within the ideal range for a domain-focused server and each tool covers a meaningful capability. The count feels appropriately scoped for GitHub browsing, issue interaction, and pull request review without being bloated.

    Completeness4/5

    The server covers read-heavy repository activity well, including search, file access, commits, issues, pull requests, and user profiles. Issue comments are supported, but lifecycle operations like updating/ closing issues or creating/merging pull requests are absent, which is a minor gap if the server is intended for broader GitHub management.

    Maintenance

    ActivityInactive
    ResponsivenessNo recent community issues

    Related MCP Connectors

    Related MCP Servers