MCP Server Mlflow

🚀 MLflow Prompt Registry MCP Server

The Model Context Protocol (MCP) server implemented for the MLflow Prompt Registry, enabling access to prompt templates managed in MLflow.

This server implements the MCP Prompts specification to discover and use prompt templates hosted in MLflow. The primary use case is to load prompt templates into Claude Desktop, allowing users to conveniently instruct Claude to handle repetitive tasks or common workflows.

🚀 Quick Start

✨ Features

Tools

• list-prompts:
  • Lists available prompts.
  • Input:
    • cursor (optional string): A cursor for pagination.
    • filter (optional string): Prompt filtering criteria.
  • Return: A list of prompt objects.
• get-prompt:
  • Retrieves and compiles a specific prompt.
  • Input:
    • name (string): The name of the prompt to retrieve.
    • arguments (optional object): A JSON object containing prompt variables.
  • Return: A compiled prompt object.

📦 Installation

Step 1: Install MLflow and Start the Prompt Registry

If not already installed, install and start the MLflow server to host the prompt registry:

pip install mlflow>=2.21.1
mlflow server --port 5000

Step 2: Create Prompt Templates in MLflow

If you haven't already, follow this guide to create prompt templates in MLflow.

Step 3: Build the MCP Server

npm install
npm run build

Step 4: Add the Server to Claude Desktop

Configure Claude for Desktop by editing claude_desktop_config.json:

{
  "mcpServers": {
    "mlflow": {
      "command": "node",
      "args": ["<absolute-path-to-this-repository>/dist/index.js"],
      "env": {
        "MLFLOW_TRACKING_URI": "http://localhost:5000"
      }
    }
  }
}

Make sure to replace MLFLOW_TRACKING_URI with your actual MLflow server address.