Ruiyu MA

v1.0.4Version Controlstable

Connect AI assistants to GitHub - manage repos, issues, PRs, and workflows through natural language.

githubmcpmcp-server
Share:
30,060
Stars
0
Downloads
0
Weekly
0/5

What is Ruiyu MA?

Ruiyu MA is a Model Context Protocol (MCP) server that allows AI assistants like Claude, Cursor, and VS Code to connect ai assistants to github - manage repos, issues, prs, and workflows through natural language.

Connect AI assistants to GitHub - manage repos, issues, PRs, and workflows through natural language.

This server falls under the Version Control category on MCPgee, the world's largest MCP server directory with 33,000+ servers.

Features

  • Connect AI assistants to GitHub - manage repos, issues, PRs,

Use Cases

GitHub integration
Repository management
Natural language git control
github

Maintainer

LicenseMIT
Languagego
Versionv1.0.4
UpdatedMay 22, 2026
Statushealthy
Maintenanceactive

Works with

ClaudeOpenAIwindowsmacoslinux

Installation

Manual Installation

npx ruiyu-ma

Configuration

Configuration Details

Config File

claude_desktop_config.json

Performance

Response Metrics

Response Time< 200ms
ThroughputMedium

Resource Usage

Memory UsageLow
CPU UsageLow

How to Set Up and Use Ruiyu MA

The GitHub MCP Server (tagged here as ruiyu-ma) is the official MCP server published by GitHub that connects AI assistants to the full GitHub API through natural language. It exposes toolsets for managing repositories, issues, pull requests, GitHub Actions workflows, code scanning alerts, Dependabot vulnerabilities, GitHub Discussions, and GitHub Projects — all as MCP tool calls. Engineering teams use it to let AI assistants triage issues, review PRs, monitor CI pipelines, and search across code without leaving their AI client.

Prerequisites

  • A GitHub account and a Personal Access Token (PAT) — classic or fine-grained — with scopes matching the toolsets you want to use
  • Docker installed (for the simplest deployment), or Go 1.21+ if building from source
  • An MCP-compatible client such as Claude Desktop, Cursor, or VS Code with MCP support
  • For GitHub Enterprise Server: the server's base URL (must be prefixed with https://)
1

Generate a GitHub Personal Access Token

Go to GitHub Settings > Developer settings > Personal access tokens and create a fine-grained or classic token. For read-only use, grant: repo (read), issues (read), pull_requests (read). For write operations also include: issues (write), pull_requests (write), actions (read).

# Set the token as an environment variable for use below
export GITHUB_PERSONAL_ACCESS_TOKEN=github_pat_...
2

Test the server with Docker

Run the official Docker image to verify the server starts and authenticates correctly before adding it to your MCP client.

docker run -i --rm \
  -e GITHUB_PERSONAL_ACCESS_TOKEN \
  ghcr.io/github/github-mcp-server
3

Add to your MCP client configuration

Configure your MCP client to run the GitHub MCP server via Docker, passing the token as an environment variable.

{
  "mcpServers": {
    "github": {
      "command": "docker",
      "args": [
        "run", "-i", "--rm",
        "-e", "GITHUB_PERSONAL_ACCESS_TOKEN",
        "ghcr.io/github/github-mcp-server"
      ],
      "env": {
        "GITHUB_PERSONAL_ACCESS_TOKEN": "github_pat_YOUR_TOKEN_HERE"
      }
    }
  }
}
4

Optional: Enable only specific toolsets

Limit the tools exposed to your AI assistant to reduce token usage and surface area. Set GITHUB_TOOLSETS to a comma-separated list of the toolsets you need.

# Available toolsets: context, repos, issues, pull_requests, actions,
# code_security, dependabot, discussions, projects, notifications
export GITHUB_TOOLSETS="repos,issues,pull_requests"
5

Optional: Enable read-only mode

Set GITHUB_READ_ONLY=1 to prevent any write operations, which is useful for CI or auditing use cases.

docker run -i --rm \
  -e GITHUB_PERSONAL_ACCESS_TOKEN \
  -e GITHUB_READ_ONLY=1 \
  ghcr.io/github/github-mcp-server

Ruiyu MA Examples

Client configuration

Full claude_desktop_config.json entry for the GitHub MCP Server using Docker, with the repos, issues, and pull_requests toolsets enabled.

{
  "mcpServers": {
    "github": {
      "command": "docker",
      "args": [
        "run", "-i", "--rm",
        "-e", "GITHUB_PERSONAL_ACCESS_TOKEN",
        "-e", "GITHUB_TOOLSETS",
        "ghcr.io/github/github-mcp-server"
      ],
      "env": {
        "GITHUB_PERSONAL_ACCESS_TOKEN": "github_pat_YOUR_TOKEN_HERE",
        "GITHUB_TOOLSETS": "repos,issues,pull_requests,actions"
      }
    }
  }
}

Prompts to try

Natural language prompts that exercise the GitHub MCP server's issue, PR, repo, and Actions toolsets.

- "List all open issues labeled 'bug' in the repo myorg/myrepo that haven't been updated in over 2 weeks"
- "Show me all pull requests in myorg/myrepo that are awaiting review and have no reviewer assigned"
- "Search for code using the pattern 'TODO: fix' across all repositories in my organization"
- "Summarize the last 5 workflow runs for the CI pipeline in myorg/myrepo and flag any failures"
- "Create a new issue in myorg/myrepo titled 'Memory leak in user session handler' with a description of the problem"

Troubleshooting Ruiyu MA

API calls return 401 Unauthorized

Verify your GITHUB_PERSONAL_ACCESS_TOKEN is correctly set and has not expired. Fine-grained tokens must grant permissions on the specific repositories or organization you're querying. Double-check token scopes in GitHub Settings > Developer settings > Personal access tokens.

Docker image pull fails or server doesn't start

Ensure Docker is running and you can pull from ghcr.io: 'docker pull ghcr.io/github/github-mcp-server'. If you're behind a corporate proxy, configure Docker's HTTP_PROXY settings. Alternatively, build from source with 'go build -o github-mcp-server ./cmd/github-mcp-server' from the cloned repo.

Tools for Actions or code scanning are missing from the tool list

These capabilities are in separate toolsets. Set GITHUB_TOOLSETS to include 'actions' and/or 'code_security'. If you set GITHUB_TOOLSETS to a specific list, only those toolsets are loaded — the default loads all of them.

Frequently Asked Questions about Ruiyu MA

What is Ruiyu MA?

Ruiyu MA is a Model Context Protocol (MCP) server that connect ai assistants to github - manage repos, issues, prs, and workflows through natural language. It connects AI assistants to external tools and data sources through a standardized interface.

How do I install Ruiyu MA?

Follow the installation instructions on the Ruiyu MA GitHub repository. Clone the repo, install dependencies, and add the server config to your AI client.

Which AI clients work with Ruiyu MA?

Ruiyu MA works with all major MCP-compatible AI clients including Claude Desktop, Claude Code, Cursor, VS Code (GitHub Copilot), Windsurf, and Cline.

Is Ruiyu MA free to use?

Yes, Ruiyu MA is open source and available under the MIT license. You can use it freely in both personal and commercial projects.

Ruiyu MA Alternatives — Similar Version Control Servers

Looking for alternatives to Ruiyu MA? Here are other popular version control servers you can use with Claude, Cursor, and VS Code.

Browse More Version Control MCP Servers

Explore all version control servers available in the MCPgee directory. Each server includes setup guides for Claude, Cursor, and VS Code.

Quick Config Preview

{ "mcpServers": { "ruiyu-ma": { "command": "npx", "args": ["-y", "ruiyu-ma"] } } }

Add this to your claude_desktop_config.json or .cursor/mcp.json

Read the full setup guide →

Ready to use Ruiyu MA?

Browse our complete directory of 33,000+ MCP servers, read setup guides for your editor, and start building with the Model Context Protocol.

33,000+ ServersFree & Open SourceStep-by-Step Guides