GitHub Project Manager MCP

@marioalvial

About GitHub Project Manager MCP

MCP server wrapping the GitHub CLI (gh) to provide tools for managing GitHub resources

Config

Add this server to your MCP-compatible client using the configuration below.

{
  "mcpServers": {
    "gh-project-manager": {
      "command": "docker",
      "args": [
        "run",
        "-i",
        "--rm",
        "-e",
        "GH_TOKEN",
        "ghcr.io/marioalvial/gh-project-manager-mcp"
      ],
      "env": {
        "GH_TOKEN": ""
      }
    }
  }
}

Tools

No tools detected

We auto-extract tools from the README. The maintainer can list them under a ## Tools heading to populate this section.

Overview

What is GitHub Project Manager MCP?

A model context protocol (MCP) server that manages GitHub projects via the GitHub CLI (gh). It handles common operations like issues and pull requests, with planned support for GitHub Projects. It is intended for developers using AI assistants that support MCP.

How to use GitHub Project Manager MCP?

Run the server as a Docker container with your GitHub token set as an environment variable. The image is published as ghcr.io/marioalvial/gh-project-manager-mcp. Example command: docker run -i --rm -e GH_TOKEN=your_token ghcr.io/marioalvial/gh-project-manager-mcp. Configuration for the Cursor editor is provided in the README.

Key features of GitHub Project Manager MCP

Issue creation, retrieval, and management
Pull request creation, retrieval, and management
Future integration with GitHub Projects
Docker‑based deployment with no local installation
Integration test suite for direct GitHub API interaction

Use cases of GitHub Project Manager MCP

Automate issue triage via an AI assistant
Create or review pull requests through conversational commands
Manage a repository’s workflow without leaving the chat interface

FAQ from GitHub Project Manager MCP

How do I configure the server in Cursor?

Add the provided JSON configuration to your .cursor/mcp.json. It runs the Docker container with the GH_TOKEN environment variable set to your GitHub token.

What tools does the server currently offer?

The server provides tools for managing GitHub issues and pull requests. Support for GitHub Projects is planned for the future.

What permissions are required for the GitHub token?

The token needs at least the repo and project scopes to interact with repositories and projects.

How can I run the integration tests?

Set the environment variables GH_INTEGRATION_TEST_TOKEN, GH_INTEGRATION_TEST_OWNER, GH_INTEGRATION_TEST_REPO, and optionally GH_INTEGRATION_TEST_PROJECT_ID, then run make function-integration-test. Tests create real resources on GitHub.

Where does the data from this server live?

All data stays on GitHub’s servers; the server only acts as a bridge between the MCP client and the GitHub API. No additional storage is used.

Frequently asked questions

How do I configure the server in Cursor?

Add the provided JSON configuration to your `.cursor/mcp.json`. It runs the Docker container with the `GH_TOKEN` environment variable set to your GitHub token.

What tools does the server currently offer?

The server provides tools for managing GitHub issues and pull requests. Support for GitHub Projects is planned for the future.

What permissions are required for the GitHub token?

The token needs at least the `repo` and `project` scopes to interact with repositories and projects.

How can I run the integration tests?

Set the environment variables `GH_INTEGRATION_TEST_TOKEN`, `GH_INTEGRATION_TEST_OWNER`, `GH_INTEGRATION_TEST_REPO`, and optionally `GH_INTEGRATION_TEST_PROJECT_ID`, then run `make function-integration-test`. Tests create real resources on GitHub.

Where does the data from this server live?

All data stays on GitHub’s servers; the server only acts as a bridge between the MCP client and the GitHub API. No additional storage is used.

Comments

Basic information

More Version Control MCP servers

Atlassian Bitbucket MCP Server

aashari

Node.js/TypeScript MCP server for Atlassian Bitbucket. Enables AI systems (LLMs) to interact with workspaces, repositories, and pull requests via tools (list, get, comment, search). Connects AI directly to version control workflows through the standard MCP interface.

157