# mlflow MCP server

MLflow MCP — experiments, runs, registered models, versions, traces, assessments (MLflow 3)

## Links
- Registry page: https://www.getdrio.com/mcp/io-github-us-all-mlflow
- Repository: https://github.com/us-all/mlflow-mcp-server

## Install
- Command: `npx -y @us-all/mlflow-mcp`
- Auth: Auth required by registry metadata

## Setup notes
- Package: Npm @us-all/mlflow-mcp v1.11.2
- Environment variable: MLFLOW_TRACKING_URI (required)
- Environment variable: MLFLOW_TRACKING_TOKEN (secret)
- Environment variable: MLFLOW_TRACKING_USERNAME
- Environment variable: MLFLOW_TRACKING_PASSWORD (secret)
- Environment variable: MLFLOW_EXPERIMENT_ID
- Environment variable: MLFLOW_TOOLS
- Environment variable: MLFLOW_DISABLE
- Environment variable: MLFLOW_ALLOW_WRITE (default false)
- The upstream registry signals required auth or secrets.

## Tools
Not captured

## Resources
Not captured

## Prompts
Not captured

## Metadata
- Owner: io.github.us-all
- Version: 1.11.2
- Runtime: Npm
- Transports: STDIO
- License: Not captured
- Language: Not captured
- Stars: Not captured
- Updated: May 6, 2026
- Source: https://registry.modelcontextprotocol.io