Which integrations are available for this server?

Enables comprehensive interaction with GitHub repositories, providing tools to search repositories, manage issues and pull requests, browse file contents, and handle branches and commits. Allows for the management of GitHub Actions workflows, including listing workflow files, monitoring workflow run status, and triggering manual workflow dispatches.

How do I use GitHub MCP Server?

1. Click on "Install Server". 2. Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state. 3. In the chat, type @ followed by the MCP server name and your instructions, e.g., "@GitHub MCP Server show me open issues labeled 'bug' in microsoft/vscode" That's it! The server will respond to your query, and you can continue using it as needed. Here is a step-by-step guide with screenshots.

GitHub MCP Server

A Model Context Protocol (MCP) server that enables LLMs to interact with GitHub repositories, issues, pull requests, workflows, and more.

Features

Repository Management

search_repositories - Search repos by query, language, stars
get_repository - Get detailed repo information
list_repository_files - Browse directory contents
get_file_contents - Read file content

Issue Tracking

list_issues - List/filter issues by state, labels, assignee
get_issue - Get issue details with comments
create_issue - Create new issues
update_issue - Update existing issues
add_issue_comment - Comment on issues

Pull Requests

list_pull_requests - List PRs with filters
get_pull_request - Get PR details with diff stats
create_pull_request - Create new PRs
list_pr_files - List changed files
merge_pull_request - Merge PRs (merge/squash/rebase)

Branches & Commits

list_branches - List branches with protection status
get_commits - Get commit history
compare_commits - Compare branches/tags/commits

GitHub Actions

list_workflows - List workflow files
get_workflow_runs - Get recent workflow runs
trigger_workflow - Dispatch workflow runs

Code Search

search_code - Search code across repositories

Users & Organizations

get_user - Get user/org profile
list_user_repos - List user's repositories

Installation

# Clone the repository git clone https://github.com/yourusername/github-mcp-server.git cd github-mcp-server # Create virtual environment python -m venv venv source venv/bin/activate # Linux/Mac # or venv\Scripts\activate # Windows # Install dependencies pip install -r requirements.txt

Configuration

GitHub Token

Create a Personal Access Token at https://github.com/settings/tokens with these scopes:

repo - Full control of private repositories
read:org - Read organization membership
workflow - Update GitHub Action workflows

Set the token as an environment variable:

# Linux/Mac export GITHUB_TOKEN=ghp_your_token_here # Windows (PowerShell) $env:GITHUB_TOKEN = "ghp_your_token_here" # Windows (CMD) set GITHUB_TOKEN=ghp_your_token_here

Usage

Running the Server

# Direct execution python github_mcp_server.py # With MCP Inspector (development) uv run mcp dev github_mcp_server.py # With MCP CLI uv run mcp run github_mcp_server.py

Claude Desktop Integration

Add to your Claude Desktop config (~/.config/claude/claude_desktop_config.json):

{ "mcpServers": { "github": { "command": "python", "args": ["/path/to/github_mcp_server.py"], "env": { "GITHUB_TOKEN": "ghp_your_token_here" } } } }

Tool Examples

Search Repositories

search_repositories("kubernetes helm language:go stars:>1000")

Get Repository Info

get_repository("microsoft", "vscode")

List Issues

list_issues("owner", "repo", state="open", labels="bug,help wanted")

Create Issue

create_issue("owner", "repo", "Bug: Login fails", body="Steps to reproduce...", labels=["bug"])

List Pull Requests

list_pull_requests("owner", "repo", state="open")

Create Pull Request

create_pull_request("owner", "repo", "Add feature X", "feature-branch", "main")

Search Code

search_code("import tensorflow language:python")

Get Workflow Runs

get_workflow_runs("owner", "repo", branch="main", status="completed")

Response Formats

All tools support two response formats:

markdown (default) - Human-readable formatted output
json - Structured data for programmatic use

get_repository("owner", "repo", format="json")

Error Handling

The server provides actionable error messages:

Rate Limiting: Indicates when limits reset
Not Found: Suggests verifying resource exists
Authentication: Prompts to check token validity
Validation: Lists specific field errors

Architecture

github_mcp_server.py ├── Configuration (API_BASE_URL, CHARACTER_LIMIT) ├── Enums (ResponseFormat, IssueState, PRMergeMethod) ├── Pydantic Models (input validation) ├── API Client Helpers (github_request, truncate_content) ├── Repository Tools (search, get, list files, read) ├── Issue Tools (list, get, create, update, comment) ├── Pull Request Tools (list, get, create, merge) ├── Branch & Commit Tools (list, history, compare) ├── Actions Tools (workflows, runs, trigger) ├── Code Search Tool ├── User Tools (profile, repos) └── Server Entry Point

Development

Testing Syntax

python -m py_compile github_mcp_server.py

Running in Development

# With MCP Inspector uv run mcp dev github_mcp_server.py

License

MIT License

Author

Hansen Nkefor

GitHub MCP Server

GitHub MCP Server

Features

Repository Management

Issue Tracking

Pull Requests

Branches & Commits

GitHub Actions

Code Search

Users & Organizations

Installation

Configuration

GitHub Token

Usage

Running the Server

Claude Desktop Integration

Tool Examples

Search Repositories

Get Repository Info

List Issues

Create Issue

List Pull Requests

Create Pull Request

Search Code

Get Workflow Runs

Response Formats

Error Handling

Architecture

Development

Testing Syntax

Running in Development

License

Author

Resources

New MCP Servers

Latest Blog Posts

MCP directory API