MCP.Market

Mlflow MCP server

by us-all·io.github.us-all/mlflow·v1.12.7·1 stars
No reviews yet

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

B80/100grade B
Write a reviewInstall
What users say
No reviews yet
Be the first
Safety scan
B80/100

full report

Adoption
New

1 stars45 downloads/wk

Reviews

Write one

Nobody has reviewed Mlflow yet.

If you have run it, two minutes of your experience saves the next person an afternoon.

Mlflow tools

No tool declarations could be read from the package source. They show once the server is installed.

Public scan report

scanner v0.1.9 · 2026-09-26 · same rubric, same numbers if you re-run it

no findings
  • Code scan36 source files scanned25/25
  • –Live reliabilityno gateway calls yet and no remote to proben/a
  • –Tool poisoningtools not inspected (local package is not executed); not countedn/a
  • Auth qualitystatic API keys via environment variables6/15
  • Maintenancelast push 79 days ago12/15
  • Maintainer identityregistry namespace matches repository owner; GitHub account older than a year9/10
Overall 80/100. Components that don't apply are left out of the denominator. Any critical finding is an F.RubricAppeal a findingJSON

How Mlflow compares

Against every graded MCP server, from our own scans and uptime checks. Updated after each scan run.

Safety score
80/100
higher than 60% of 48,273 servers
GitHub stars
1
more than 65% of 28,534 servers
Downloads a week
45
more than 39% of 11,915 servers with a package

Install Mlflow in Claude Code, Cursor or VS Code

Runs npx -y @us-all/mlflow-mcp on your machine. Read the scan report first; the gateway never runs local packages.

claude mcp add mlflow -- npx -y @us-all/mlflow-mcp
Add to Cursor

What the publisher says

From the Mlflow repository's README, as published. We do not edit it. Read it on GitHub

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-experiment returns experiment + topN runs + metric stats (min/max/mean) in one call from already-fetched data, zero extra round-trips. summarize-run dedups metricHistory.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 — extractFields projection on get-run / search-runs / search-traces / get-trace / fat reads, MLFLOWTOOLS / MLFLOWDISABLE 8 categories, search-tools meta-tool.
  • Apps SDK card — compare-runs renders 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 MCPTRANSPORT=http for ChatGPT Apps SDK or remote clients (Bearer auth via MCPHTTP_TOKEN).

Try this — 5 prompts

Connect the server to Claude Desktop or Claude Code, then paste any of these:

  1. Best run — "In the customer-churn-v3 experiment, find the run with the highest valaccuracy. Show its hyperparameters and metric history."*
  2. Failure mode clustering — "Find traces with status=ERROR from the last 24h in experiment 12. Group the failures by exception type and surface the 3 most common."
  3. Run comparison — "Compare the top 5 runs of experiment 12 by validationloss. Show differing hyperparameters in a table."*
  4. Model promotion — "Get the latest version of recommendationv2 registered model with the champion alias. Show its training metrics + lineage to the source run."*
  5. Trace deep-dive — "Pull trace tr-abc123. Highlight slow spans and any failed feedback annotations." (Add list-trace-attachments on Databricks workspaces.)

When to use this vs alternatives

Shortened. The full README is on GitHub.

Nothing above is checked by us. What we check is on the safety report.

Mlflow: common questions

Is Mlflow MCP server safe?
Mostly: it is graded B (80/100). Read the Mlflow safety report
How do I install Mlflow?
It runs on your machine. Copy the Claude Code, Cursor, VS Code or Claude Desktop config from the install section.
Does Mlflow need an API key?
Yes. The registry entry asks for MLFLOW_TRACKING_TOKEN, MLFLOW_TRACKING_PASSWORD.
Is Mlflow maintained?
The last commit was 115 days ago (2026-07-10). The latest release is v1.12.7.
How does Mlflow compare with other MCP servers?
safety score 80/100 (higher than 60% of 48,273 servers); github stars 1 (more than 65% of 28,534 servers); downloads a week 45 (more than 39% of 11,915 servers with a package). Full comparison.

More from us-all →