Medullar MCP Server

🚀 Medullar MCP Server

A server for retrieving Medullar Space data using the MCP protocol.

🚀 Quick Start

The Medullar MCP Server is designed to retrieve data from Medullar Space using the MCP protocol. Here's a guide to get you started.

✨ Features

• Retrieve Medullar Space data via the MCP protocol.
• Support for different running modes, including development and production.
• Provide API endpoints to access user's Medullar spaces.

📦 Installation

Prerequisites

• Python 3.10 or higher.
• uv package manager (recommended).
• A Medullar JWT token.

Setup Steps

1. Install dependencies using uv:

brew install uv
uv pip install -r requirements.txt

2. Create a .env file in the project root directory and add your Medullar JWT:

MEDULLAR_JWT=your_jwt_token_here

💻 Usage Examples

Development Mode

The fastest way to test and debug the server is to use MCP Inspector:

mcp dev server.py

Production Installation

Once the server is ready, install it to Claude Desktop with the following command:

mcp install server.py

Direct Execution

For advanced scenarios such as custom deployments:

python server.py
# Or
mcp run server.py

📚 Documentation

Environment Variables

The server requires the following environment variables:

• MEDULLAR_JWT: Your Medullar authentication token.

These variables can be provided in the following ways:

• A .env file in the project root directory.
• Environment variables in your shell.
• Using the mcp install command with the -v flag.

API Endpoints

The server provides the following endpoints:

get_medullar_spaces

Retrieve the user's Medullar spaces, which contain their curated data.

The returned space list is in the following format:

[
    {
        "name": "Space Name",
        "uuid": "Space Unique Identifier",
        "context": "Space Context"
    }
]

📄 License

For detailed information about the version history and changes, please refer to CHANGELOG.md.