MLflow MCP Server
The widest-coverage MLflow MCP — including MLflow 3 traces, prompt-optimization, webhooks, and Databricks trace attachments that no other MCP exposes.
82 tools across experiments, runs, registry, logged models, traces, assessments, webhooks, prompt-optimization. Aggregation tools (
summarize-experiment,summarize-run) fold 3–5 round-trips into one structured response with already-fetched metric stats.
What it does that others don't
- Full coverage — only third-party MLflow MCP shipping prompt-optimization-jobs (5 tools), webhooks (6), MLflow 3 LoggedModel (8), and Databricks trace attachments (
list-trace-attachments,get-trace-attachment— Databricks MLflow only; OSS returns 404). - Aggregation tools —
summarize-experimentreturns experiment + topN runs + metric stats (min/max/mean) in one call from already-fetched data, zero extra round-trips.summarize-rundedupsmetricHistory.history.*.key(~100KB savings on 4k-point series). - MCP Prompts (4) —
debug-failed-traces,promote-best-run,compare-top-runs,annotate-trace-quality. Workflow templates the model invokes directly. - MCP Resources (6) —
mlflow://run/{runId},mlflow://experiment/{expId},mlflow://run/{runId}/artifacts,mlflow://experiment/{expId}/runs,mlflow://registered-model/{name}/versions,mlflow://trace/{traceId}. - Token-efficient by design —
extractFieldsprojection onget-run/search-runs/search-traces/get-trace/ fat reads,MLFLOW_TOOLS/MLFLOW_DISABLE8 categories,search-toolsmeta-tool. - Apps SDK card —
compare-runsrenders as a side-by-side card on ChatGPT clients (run summary + metric/param tables with diff highlight) via_meta["openai/outputTemplate"]. Claude clients receive the same JSON content. - stdio + Streamable HTTP — defaults to stdio. Set
MCP_TRANSPORT=httpfor ChatGPT Apps SDK or remote clients (Bearer auth viaMCP_HTTP_TOKEN).






