A comprehensive Model Context Protocol server that empowers AI agents to manage GitHub repositories, code files, issues, and pull requests autonomously.
Install & Download
1. ClawHub CLI
The fastest way to install a skill directly from the registry.
npx clawhub@latest install github-mcp
2. Manual Installation
Copy the skill folder to one of these locations
~/.openclaw/skills/ <project>/skills/ Priority: Workspace > Local > Bundled
3. Prompt Installation
Copy this prompt to OpenClaw to install it automatically.
Help me install github-mcp using Clawhub. If Clawhub is not installed, install it first (npm i -g clawhub).
Prefer to download?
Get the raw skill files in a ZIP archive.
What is GitHub MCP Server?
The GitHub MCP Server serves as a powerful bridge between AI agents and the entire GitHub ecosystem. It allows agents to perform complex operations such as cloning repositories, searching codebases, and managing the full development lifecycle without requiring manual API integration. By utilizing Openclaw Skills like this one, developers can offload repetitive tasks—including documentation updates, code reviews, and repository maintenance—to their AI assistants.
This integration is designed for secure, agent-native workflows, supporting both classic and fine-grained GitHub tokens to ensure that your source code remains protected while providing the agent with exactly the permissions it needs. Whether you are building a custom coding assistant or automating a CI/CD pipeline, this skill provides the tools necessary to interact with the GitHub API as a first-class citizen.
GitHub MCP Server Use Cases
- Automating code review processes by scanning pull requests for security vulnerabilities or style guide compliance.
- Synchronizing technical documentation by extracting docstrings from source code and updating Markdown files or READMEs.
- Managing repository maintenance tasks such as labeling new issues, triaging bug reports, and organizing project boards.
- Streamlining release management by automatically creating branches, updating version numbers in package files, and generating changelogs.
How GitHub MCP Server Works
- The AI agent initializes the connection through the Openclaw Skills framework using a configured GitHub Personal Access Token.
- When a user provides a natural language prompt, the agent selects the appropriate tool, such as search_code or create_pull_request, from the MCP server's toolkit.
- The MCP server translates the agent's intent into a structured GitHub REST API call with the correct headers and parameters.
- GitHub processes the request and returns the resulting data or status code back to the server.
- The server parses the response and provides the agent with the updated context, allowing it to complete the task or continue to the next step in a multi-stage workflow.
GitHub MCP Server Setup
To begin using this among other Openclaw Skills, you can install the server globally via npm:
npm install -g @modelcontextprotocol/server-github
Next, configure your MCP client by adding the server details and your GITHUB_PERSONAL_ACCESS_TOKEN to your configuration file:
{
"mcpServers": {
"github": {
"command": "npx",
"args": ["-y", "@modelcontextprotocol/server-github"],
"env": {
"GITHUB_PERSONAL_ACCESS_TOKEN": "your_ghp_token_here"
}
}
}
}
GitHub MCP Server Data Schema & Taxonomy
The GitHub MCP skill organizes and interacts with data according to the standard GitHub API taxonomy. Key data points include:
| Data Category | Description |
|---|---|
| Repository Metadata | Name, owner, visibility, and directory structures. |
| File Content | Source code blobs, encoded in UTF-8 or Base64, including file paths. |
| Collaboration Data | Issue titles, body content, labels, and Pull Request diffs. |
| Git Refs | Branch names, commit hashes, and release tags. |
| Audit Logs | History of actions performed by the agent through the GitHub API. |
GitHub MCP Server Advanced Features
- Support for fine-grained tokens to restrict agent access to specific repositories and read/write permissions.
- Automatic pagination handling to allow agents to process large repositories and search results without manual oversight.
- Integration with GitHub Enterprise by configuring custom GITHUB_API_URL environment variables.
- Capability to trigger and monitor GitHub Actions workflows, facilitating end-to-end CI/CD automation.
- Advanced code search capabilities that allow agents to identify patterns and dependencies across multiple repositories.
SKILL.md
Loading
Related Openclaw Skills
Filesystem MCP Server
A secure, sandboxed Model Context Protocol server that enables AI agents to perform file and directory operations within explicitly allowed paths.
PayRam Crypto Payments
A self-hosted, non-custodial cryptocurrency payment gateway that enables keyless fund management across multiple blockchain networks.
PayRam Crypto Payments for SaaS
Enable USDC-based subscriptions, usage billing, and automated invoicing for SaaS products using the PayRam MCP server.
Brave Search MCP Server
A privacy-focused Model Context Protocol server that empowers AI agents with comprehensive web, image, news, and local search capabilities without tracking.
PayRam vs x402 Comparison Skill
A technical reference for comparing self-hosted PayRam infrastructure with the x402 HTTP payment protocol for AI agent commerce.
HokiPoki
A CLI-based P2P tool for routing tasks to different AI models and sharing subscriptions securely within teams.
Featured*
