MlflowAgent MCP Server

mcp server for mlflow

Local serverstdioPython

What is the MlflowAgent MCP server?

Most developer tooling work still happens through a UI a human drives. MlflowAgent MCP server moves it into the conversation instead. mcp server for mlflow.

The short version

This project provides a natural language interface to MLflow via the Model Context Protocol (MCP). It allows you to query your MLflow tracking server using plain English, making it easier to manage and explore your machine learning experiments and models.

  1. MLflow MCP Server (mlflow_server.py): Connects to your MLflow tracking server and exposes MLflow functionality through the Model Context Protocol (MCP).
  • Natural Language Queries — Ask questions about your MLflow tracking server in plain English
  • Model Registry Exploration — Get information about your registered models
  • Experiment Tracking — List and explore your experiments and runs
  • System Information — Get status and metadata about your MLflow environment

Getting it running

Installation goes through your MCP client rather than a global install: point it at @smithery/cli on npm and it is fetched when the client starts. The copy-paste blocks for Claude Desktop, Claude Code and Cursor are further down this page.

What it needs from you

Configuration is passed through the environment: OPENAI_API_KEY, MLFLOW_TRACKING_URI. Treat anything key-shaped as a real credential — scope it to the minimum the server needs, and rotate it if it ever lands in a shared config.

  • Python 3.8+ - MLflow server running (default: http://localhost:8080) - OpenAI API key for the LLM

How it compares

Among the developer tooling options, the useful question is rarely "what can it do" but "what does it cost you to run" — permissions, credentials, and how much of your context its toolset consumes. It is maintained by iRahulPandey; worth a glance at recent repository activity before you build anything load-bearing on it.

This entry was verified against MlflowAgent's own documentation before publication; SyncDev keeps the directory reviewed rather than auto-generated.

Things to watch

  • It runs with your machine's permissions. That is convenient and also the reason to think about what you point it at before you approve a tool call.
  • Missing credentials fail quietly in some clients — if no tools show up, check the environment block first.
  • Keep per-call confirmation enabled while you learn its behaviour; it is the cheapest safeguard you have.

How to install the MlflowAgent MCP server

{
  "mcpServers": {
    "mlflowagent": {
      "command": "npx",
      "args": ["-y", "@smithery/cli"],
      "env": {
        "OPENAI_API_KEY": "your-value",
        "MLFLOW_TRACKING_URI": "your-value"
      }
    }
  }
}

Add to claude_desktop_config.json, then restart Claude Desktop.

Configuration

  • Python 3.8+ - MLflow server running (default: http://localhost:8080) - OpenAI API key for the LLM
VariableDescriptionRequired
OPENAI_API_KEYCredential the server authenticates with.Yes
MLFLOW_TRACKING_URIConfiguration value read at startup.Optional

Frequently asked questions

Python 3.8+, an MLflow tracking server (default `http://localhost:8080`), and an OpenAI API key for the LLM component.