GitHub Actions MCP server

The GitHub Actions MCP Server serves as a Model Context Protocol interface for the GitHub Actions API, allowing AI assistants to manage and execute GitHub Actions workflows efficiently. It provides a comprehensive set of tools for workflow management, detailed analysis, and operation.

Installation

To set up the GitHub Actions MCP Server, follow these steps:

Prerequisites

• Node.js installed on your system
• A GitHub Personal Access Token with appropriate permissions

Build from Source

Clone the repository and build the server:

git clone https://github.com/ko1ynnky/github-actions-mcp-server.git
cd github-actions-mcp-server
npm install
npm run build

This creates the necessary files in the dist directory that you'll need to run the MCP server.

Configuration

Setting up with Claude Desktop

Add the following to your claude_desktop_config.json:

{
  "mcpServers": {
    "github-actions": {
      "command": "node",
      "args": [
        "/path/to/github-actions-mcp-server/dist/index.js"
      ],
      "env": {
        "GITHUB_PERSONAL_ACCESS_TOKEN": "YOUR_GITHUB_TOKEN"
      }
    }
  }
}

Be sure to replace /path/to/github-actions-mcp-server with the actual path and YOUR_GITHUB_TOKEN with your GitHub Personal Access Token.

Available Tools

The MCP server provides the following tools:

Workflow Management

• list_workflows: List all workflows in a repository
• get_workflow: Get details about a specific workflow
• get_workflow_usage: Get usage statistics for a workflow
• trigger_workflow: Trigger a workflow run
• cancel_workflow_run: Cancel a running workflow
• rerun_workflow: Re-run a previously executed workflow

Workflow Analysis

• list_workflow_runs: List all workflow runs with filtering options
• get_workflow_run: Get details about a specific workflow run
• get_workflow_run_jobs: Get job information for a specific workflow run

Usage Examples

Listing Workflows

const result = await listWorkflows({
  owner: "your-username",
  repo: "your-repository"
});

Getting a Specific Workflow

const result = await getWorkflow({
  owner: "your-username", 
  repo: "your-repository",
  workflowId: "ci.yml"
});

Triggering a Workflow

const result = await triggerWorkflow({
  owner: "your-username",
  repo: "your-repository",
  workflowId: "ci.yml",
  ref: "main",
  inputs: {
    environment: "production"
  }
});

Listing Workflow Runs with Filters

const result = await listWorkflowRuns({
  owner: "your-username",
  repo: "your-repository",
  branch: "main",
  status: "completed",
  perPage: 50
});

Canceling a Workflow Run

const result = await cancelWorkflowRun({
  owner: "your-username",
  repo: "your-repository",
  runId: 123456789
});

Troubleshooting

Common Issues

• Authentication Errors: Ensure your GitHub token has the correct permissions and is properly set as an environment variable.

• Rate Limiting: The server implements rate limiting to avoid hitting GitHub API limits. If you encounter rate limit errors, reduce the frequency of requests.

• Type Validation Errors: GitHub API responses might sometimes differ from expected schemas. The server implements flexible validation to handle most variations.

How to add this MCP server to 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 > MCP and click "Add new global MCP server".

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

{
    "mcpServers": {
        "cursor-rules-mcp": {
            "command": "npx",
            "args": [
                "-y",
                "cursor-rules-mcp"
            ]
        }
    }
}

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 explictly ask the agent to use the tool by mentioning the tool name and describing what the function does.