mcpField
G
Github Actions

Github Actions

Local
github.com/devopsierVersion Control5Updated 79w ago

About Github Actions

Github Actions is an MCP server for developers managing GitHub repositories and workflows through clients or agents. It provides resources, tools, and prompts for triggering workflows and handling repository tasks.

Key features

  1. 01Fetch and manage repositories and workflows
  2. 02Trigger GitHub Actions workflows
  3. 03Generate prompts for creating issues

Use cases

  1. 01Inspect GitHub repositories and workflows
  2. 02Trigger repository automation workflows
  3. 03Assist with issue creation and pull request reviews

MCP support

The MCP server exposes GitHub repository and workflow resources, workflow-triggering tools, and prompts to MCP clients.

Configuration

Local server config is the same for every client. Copy it into your client’s MCP config file.

mcp.json · Universal config
{
"mcpServers": {
"github-actions": {
"command": "docker",
"args": [
"run",
"-i",
"--rm",
"build"
]
}
}
}
Run commanddocker run -i --rm build

Local servers need a runtime on your machine (e.g. Node.js 18+). Config file locations differ by client; see your client’s docs.

Packages
ocibuild

Tools

No tool list yet

Local servers expose tools only once running on your machine, and the maintainer has not provided a tool list.

Details

From the project README

GitHub Actions MCP Server

This repository contains the implementation of a Model Context Protocol (MCP) server for managing GitHub Actions workflows and resources. The server is designed to interact with GitHub repositories and provide tools, resources, and prompts for automating and managing workflows.

Features

  • Resource Management: Fetch and manage GitHub repositories and workflows.
  • Tool Execution: Trigger workflows and manage GitHub Actions tools.
  • Prompt Generation: Create issues, review pull requests, and more.

Project Structure

/app/github-actions-mcp-server
├── Dockerfile
├── package.json
├── tsconfig.json
├── src/
│   ├── http-server.ts
│   ├── server.backup.ts
│   ├── server.ts
│   ├── stdio-server.ts
│   ├── github/
│   │   └── client.ts
│   └── utils/
│       └── utils.ts

Prerequisites

  • Docker
  • Node.js (v16 or later)
  • GitHub Personal Access Token (PAT) with appropriate permissions

Setup

  1. Clone the repository:

    git clone https://github.com/devopsier/github-actions-mcp.git
    cd github-actions-mcp
    
  2. Install dependencies:

    npm install
    
  3. Build the Docker image:

    docker build -t github-actions-mcp .
    
  4. Run the server:

    docker run -i --rm -e GITHUB_TOKEN=<your_github_token> -e GITHUB_TYPE=cloud github-actions-mcp
    

Configuration

The server can be configured using the settings.json file in your VS Code workspace. Example:

"mcp": {
    "servers": {
        "mcp-github-actions": {
            "command": "docker",
            "args": [
                "run",
                "-i",
                "--rm",
                "-e",
                "GITHUB_TOKEN",
                "-e",
                "GITHUB_TYPE",
                "github-actions-mcp"
            ],
            "env": {
                "GITHUB_TOKEN": "<your_github_token>",
                "GITHUB_TYPE": "cloud"
            }
        }
    }
}

Contributing

We welcome contributions to the GitHub Actions MCP Server project! To contribute, please follow these steps:

  1. Fork the repository on GitHub.
  2. Create a new branch for your feature or bugfix:
    git checkout -b my-feature-branch
    
  3. Make your changes and commit them with clear and concise messages.
  4. Push your branch to your forked repository:
    git push origin my-feature-branch
    
  5. Open a pull request to the main repository and provide a detailed description of your changes.

For more details, see the CONTRIBUTING.md file.

License

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

Comments

Markdown supported

New to MCP?

From what the protocol is to installing your first server, these answers cover most first questions.

An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.