mcpField
M
Medullar MCP Server

Medullar MCP Server

Local
github.com/medullarMemory & Knowledge0Updated 83w ago
Repository

About Medullar MCP Server

Medullar MCP Server connects MCP clients to a user's Medullar Space data. It provides a tool to retrieve spaces and requires a Medullar JWT for authentication.

Key features

  1. 01Retrieve Medullar spaces
  2. 02Return space names, UUIDs, and context
  3. 03Authenticate with a Medullar JWT

Use cases

  1. 01Listing a user's Medullar spaces
  2. 02Retrieving space context for an MCP workflow

MCP support

Exposes `get_medullar_spaces` to MCP clients, returning the user's Medullar spaces with each space's name, UUID, and context.

Configuration

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

No install method listed yet

We haven’t collected a package or remote endpoint for this server. Follow the instructions in the project README.

Repository

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

Medullar MCP Server

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

Prerequisites

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

Setup

  1. Install dependencies using uv:
brew install uv
uv pip install -r requirements.txt
  1. Create a .env file in the project root with your Medullar JWT:
MEDULLAR_JWT=your_jwt_token_here

Running Your Server

Development Mode

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

mcp dev server.py
Production Installation

Once your server is ready, install it in Claude Desktop:

mcp install server.py
Direct Execution

For advanced scenarios like custom deployments:

python server.py
# or
mcp run server.py

Environment Variables

The server requires the following environment variables:

  • MEDULLAR_JWT: Your Medullar authentication token

These can be provided either through:

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

API Endpoints

The server provides the following endpoints:

get_medullar_spaces

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

Returns a list of spaces in the format:

[
    {
        "name": "Space Name",
        "uuid": "Space unique identification",
        "context": "Space context"
    }
]

Changelog

See CHANGELOG.md for a list of changes and version history.

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.