MLflow MCP — 82 tools for experiments, runs, registered models, traces, assessments. MLflow 3 GenAI traces support with analyze-failed-traces workflow Prompt.
Claim it to get a verified publisher badge, a free copy of our full audit findings, and direct contact for any high-priority issues we find.
Install from
M8ven verifies MCPs across every public registry — install directly from whichever one you prefer.
process.env. You'll be asked to provide them before it can run.MLFLOW_ALLOW_WRITE— ❌ false Set true to enable mutations (create/update/delete)MLFLOW_DISABLE— Token-efficient by design — extractFields projection on get-run / search-runs / search-traces / get-trace / fat reads, MLFLOW_TOOLS / 8 categories, search-tools meta-tool.MLFLOW_EXPERIMENT_ID— ❌ — Default experiment ID for tools that accept it implicitlyMLFLOW_TOOLS— Token-efficient by design — extractFields projection on get-run / search-runs / search-traces / get-trace / fat reads, / MLFLOW_DISABLE 8 categories, search-tools meta-tool.MLFLOW_TRACKING_PASSWORD— ❌ — Basic-auth passwordMLFLOW_TRACKING_TOKEN— ❌ — Bearer token. Use for Databricks PAT (dapi…)MLFLOW_TRACKING_URI— "": "http://localhost:5000"MLFLOW_TRACKING_USERNAME— ❌ — Basic-auth username (alternative to token)TOKEN_BUDGET[](https://m8ven.ai/mcp/us-all-mlflow-mcp-server-1slm3k)