Gooseworks MCP
A Model Context Protocol (MCP) server that exposes GitHub tools for repository management, code search, issue creation, and pull request operations.
README
Gooseworks MCP
An Express server that exposes tools through the Model Context Protocol (MCP) Streamable HTTP transport, including a set of GitHub tools.
The MCP endpoint is:
http://localhost:4000/mcp
Every request must include the bearer token configured by MCP_AUTH_TOKEN.
Requirements
- Node.js
v25.2.1 - pnpm
11.5.3 - Docker Engine and Docker Compose v2 for container deployment
- A GitHub personal access token with the permissions required by the tools you plan to use
Configuration
The server loads variables from a local .env file or the process environment:
| Variable | Required | Default | Description |
|---|---|---|---|
PORT |
No | 4000 |
Port on which the HTTP server listens |
GITHUB_TOKEN |
Yes | None | GitHub personal access token used by Octokit |
MCP_AUTH_TOKEN |
Yes | None | Bearer token required for every MCP request |
Create a local environment file from the template:
cp .env.template .env
Edit .env and replace both placeholder token values. Use a long, randomly generated value for MCP_AUTH_TOKEN, and grant the GitHub token only the permissions needed by this server. Never commit .env or paste either token into a public issue, log, or image.
Run Locally
-
Install dependencies:
pnpm install -
Create and configure
.envas described above. -
Start the server:
pnpm startThis runs the same entrypoint as
pnpm exec tsx src/index.ts.
For development with automatic restart after source changes, use:
pnpm dev
To check the TypeScript project without emitting files:
pnpm typecheck
The server is ready when the console reports that it is active on http://localhost:<PORT>/mcp. Configure your MCP client to use that URL and send:
Authorization: Bearer <MCP_AUTH_TOKEN>
Deploy With Docker Compose
-
Install Docker Engine with Docker Compose v2 on the host.
-
Clone this repository and enter its directory:
git clone <repository-url> cd gooseworks-mcp -
Create the deployment environment file:
cp .env.template .env -
Set
GITHUB_TOKENand a strong, privateMCP_AUTH_TOKENin.env. SetPORTif the service should listen on a different host/container port. The same value is used for both sides of the Compose port mapping. -
Build and start the service in the background:
docker compose up --build -d -
Follow the service logs or stop it when needed:
docker compose logs -f gooseworks-mcp docker compose down
The Compose configuration passes the three supported variables into the container and fails early if either required token is missing. For a public deployment, place the service behind an HTTPS reverse proxy and keep port 4000 or your chosen PORT private when possible. MCP clients should use the proxy's HTTPS /mcp URL and the configured bearer token.
Available Tools
The server registers the following tools:
GitHub
- Reading the authenticated profile
- Listing repositories, branches, and commits
- Searching code
- Reading file contents
- Creating issues
- Creating pull requests
License
This project is licensed under the MIT License. It is free to use, fork, modify, and redistribute for any purpose, subject to the license terms.
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.