Mlflow MCP Server

Model Context Protocol (MCP) Server for MLflow Prompt Registry

Local serverstdio

What is the Mlflow MCP server?

Mlflow becomes available to MCP clients through the mlflow mcp server. Model Context Protocol (MCP) Server for MLflow Prompt Registry.

What Mlflow does

Model Context Protocol (MCP) Server for MLflow Prompt Registry, enabling access to prompt templates managed in MLflow.

Tools it exposes

Once connected, the assistant can call these 4 tools directly:

  • list-prompts — List available prompts
  • Inputs — - cursor (optional string): Cursor for pagination
  • Returns — List of prompt objects
  • get-prompt — Retrieve and compile a specific prompt

Installing the mlflow mcp server

The server is distributed via npm as npm, so most clients can run it without a manual build step. Add it to your MCP client's configuration and restart the client to pick it up — the copy-paste configs for Claude Desktop, Claude Code and Cursor are on this page.

Configuration

The server reads one environment variable: MLFLOW_TRACKING_URI. Keep credentials in your client's env block or a secrets manager rather than committing them.

Where it fits

Developer-tool servers are usually the first ones people connect, because they turn "help me with this code" into an assistant that can actually read the repo and act on it. Mlflow sits in that group, and the shape of its toolset — list-prompts, Inputs, Returns among others — tells you what it is really for. Worth comparing against the other developer tools servers in this directory before you commit to one, since several overlap in scope but differ sharply in setup cost and permissions.

Practical notes

  • This server runs locally, so it operates with whatever access your machine and its credentials already have. Scope that deliberately rather than by default.
  • Maintained by B-Step62.
  • MCP clients ask for confirmation before each tool call by default. Keep that on while you learn what the mlflow mcp server actually does with your data.
  • Every entry in this directory is reviewed by hand before it goes live, and details are checked against the project's own documentation.

Available tools

ToolWhat it does
list-promptsList available prompts
Inputs- cursor (optional string): Cursor for pagination
ReturnsList of prompt objects
get-promptRetrieve and compile a specific prompt

How to install the Mlflow MCP server

{
  "mcpServers": {
    "server-mlflow": {
      "command": "npx",
      "args": ["-y", "npm"],
      "env": {
        "MLFLOW_TRACKING_URI": "your-value"
      }
    }
  }
}

Add to claude_desktop_config.json, then restart Claude Desktop.

Configuration

VariableDescriptionRequired
MLFLOW_TRACKING_URIConfiguration value read at startup.Optional

Example prompts to try

  • Use Mlflow to list-prompts.
  • Use Mlflow to Inputs.
  • Use Mlflow to Returns.

Frequently asked questions

It connects Mlflow to MCP-compatible AI assistants such as Claude and Cursor, exposing 4 tools (list-prompts, Inputs, Returns, and more) that the assistant can call on your behalf. Instead of copying data back and forth by hand, the assistant works with Mlflow directly.