MLflow MCP

AModel Context Protocol (MCP)server that enables LLMs to interact withMLflowtracking servers. Query experiments, analyze runs, compare metrics, manage the model registry, and promote models to production — all through natural language.

# Run directly without installation uvx mlflow-mcp # Or install globally pip install mlflow-mcp

git clone https://github.com/kkruglik/mlflow-mcp.git cd mlflow-mcp uv sync uv run mlflow-mcp

{ "mcpServers": { "mlflow": { "command": "uvx", "args": ["mlflow-mcp"], "env": { "MLFLOW_TRACKING_URI": "http://localhost:5000" } } } }

{ "mcpServers": { "mlflow": { "command": "uvx", "args": ["mlflow-mcp"], "env": { "MLFLOW_TRACKING_URI": "http://localhost:5000" } } } }

For MLflow servers with authentication, add credentials to theenvblock:

{ "mcpServers": { "mlflow": { "command": "uvx", "args": ["mlflow-mcp"], "env": { "MLFLOW_TRACKING_URI": "https://mlflow.company.com", "MLFLOW_TRACKING_USERNAME": "your-username", "MLFLOW_TRACKING_PASSWORD": "your-password" } } } }

For Databricks or token-based auth, useMLFLOW_TRACKING_TOKENinstead:

{ "mcpServers": { "mlflow": { "command": "uvx", "args": ["mlflow-mcp"], "env": { "MLFLOW_TRACKING_URI": "https://mlflow.company.com", "MLFLOW_TRACKING_TOKEN": "your-token" } } } }

Built-in guided workflows available as slash commands in Claude:

"Show me all experiments. Which ones were updated recently?"

"What metrics and parameters are tracked in experiment 'fraud-detection'?"

"Get the top 10 runs in 'fraud-detection' sorted by test/f1. Show me the params that differ most between the top 3."

"Find all runs tagged with model_type=lightgbm and compare their recall scores."

"Show me the full details of run abc123 — metrics, params, and artifacts."

"Plot the training loss curve for run abc123."(Claude fetches metric history and renders a chart)

"This run has a parent — show me the parent run and compare their metrics."

"Find the best logged model in experiment 'fraud-detection' by test/recall. Register it as 'fraud-classifier' with a selection_metric tag."

"Which logged model in experiments 1 and 2 has the highest F1 score on the validation set?"

"Register the model from run abc123 artifact path 'model/' as 'my-classifier'."

"Show me all versions of 'fraud-classifier' with their aliases and stages."

"Set the champion alias on version 3 of fraud-classifier."

"Update the description of fraud-classifier v3 to explain what dataset it was trained on."

"Copy fraud-classifier v3 to a separate 'fraud-classifier-prod' model as the production entry."

(Triggers theaudit_mlflow_setupbuilt-in prompt — Claude explores experiments, runs, artifacts, and the model registry, then scores each area against Google/Databricks best practices)

| Category | Score | Top Issue | |----------------------|--------|------------------------------------------------| | Experiment Org | 5/10 | Flat namespace, no dot-notation hierarchy | | Parameter Logging | 7/10 | No parent-child nesting for tuning sweeps | | Metric Logging | 6/10 | Only final values logged, no training curves | | Tagging Strategy | 5/10 | Params duplicated as tags; stale test_tag | | Artifact Management | 2/10 | No log_model(); artifacts on local disk | | Model Registry | 3/10 | Duplicate prod models instead of aliases | | Reproducibility | 3/10 | No git SHA; no mlflow.log_input() datasets | | Mean Score | 4.4/10| | Top 3 improvements: 1. Call log_model() and move artifact store to S3/GCS 2. Add git SHA tag + mlflow.log_input() for dataset tracking 3. Consolidate registry to one model entry with @champion alias

"Find the best model in 'fraud-detection' by test/recall, register it as 'fraud-classifier', tag it with the framework and problem type, and set it as champion. Ask me before copying to prod."

(This maps directly to thepromote_best_modelbuilt-in prompt)

UseMCP Inspectorto browse tools, call them with custom inputs, and inspect raw responses — without involving an LLM.

npx @modelcontextprotocol/inspector uvx mlflow-mcp

npx @modelcontextprotocol/inspector uv run --project /path/to/mlflow-mcp mlflow-mcp

MLFLOW_TRACKING_URI=http://127.0.0.1:5000 npx @modelcontextprotocol/inspector uvx mlflow-mcp

MIT License - seeLICENSEfile for details.

- PyPI Package
- GitHub Repository
- MLflow Documentation
- Model Context Protocol

Coral Query Plane is a paid remote MCP endpoint for AI SDK data query MCP. It exposes structured JSON tools, a public server card, token-based access, usage receipts, and audit-ready workflo