io.github.us-all/mlflow

@us-all/mlflow-mcp

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

1 51/wk 10 tools GitHub npm

No known CVEs

MIT license

Maintained

Last commit 48d ago

Works with most clients

Transport: stdio, sse, http

10 tools · ~455 tok

Grade A · 0.2% of 200K ctx

MCPpedia last refreshed this data 5m ago

Edit this pageView history

io.github.us-all/mlflow is an MCP server that MLflow MCP — experiments, runs, registered models, versions, traces, assessments (MLflow 3). Its tool list has not been published yet over stdio, sse and http, requires no API key, and scores 82/100 on MCPpedia's security, maintenance and efficiency rubric.

Other

Step 1

Install in your client

Config is the same across clients — only the file and path differ.

Supported in Claude Desktopstdio, sse, http · Node 18+

Paste into ~/Library/Application Support/Claude/claude_desktop_config.json

{
  "mcpServers": {
    "mlflow": {
      "env": {
        "MLFLOW_TRACKING_URI": "http://localhost:5000"
      },
      "args": [
        "-y",
        "@us-all/mlflow-mcp"
      ],
      "command": "npx"
    }
  }
}

Are you the author?

Add this badge to your README to show your security score and help users find safe servers.

Embed in your READMEAbout badges →

[![MCPpedia Score](https://mcppedia.org/api/badge/io-github-us-all-mlflow)](https://mcppedia.org/s/io-github-us-all-mlflow)

Read me

What io.github.us-all/mlflow does

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.

Test This Server

Run this in your terminal to verify the server starts. Then let us know if it worked — your result helps other developers.

npx -y '@us-all/mlflow-mcp' 2>&1 | head -1 && echo "✓ Server started successfully"

After testing, let us know if it worked:

Scored, not listed

Why this score

Five weighted categories — click any category to see the underlying evidence.

Score breakdown

82/100across 5 weighted dimensions

How we score →

0255075100

−18

Security

Maintenance

Efficiency

Documentation

Compatibility

Categoriesclick a row to see evidence

Security

OSV.dev

No known CVEs.

Checked @us-all/mlflow-mcp against OSV.dev.

Inventory

Tools (10)

Click any tool to inspect its schema.

~455 tokens total

Inventory

Resources (6)

mlflow run

MLflow run resource

mlflow://run/{runId}

mlflow experiment

MLflow experiment resource

mlflow://experiment/{expId}

mlflow run artifacts

MLflow run artifacts resource

mlflow://run/{runId}/artifacts

mlflow experiment runs

MLflow experiment runs resource

mlflow://experiment/{expId}/runs

mlflow registered model versions

MLflow registered model versions resource

mlflow://registered-model/{name}/versions

mlflow trace

MLflow trace resource

mlflow://trace/{traceId}

Inventory

Prompts (4)

debug-failed-traces

Find failed traces, group failure modes

promote-best-run

Find best run, register model, and set champion alias

compare-top-runs

Compare top runs by metric

annotate-trace-quality

Highlight slow spans and failed feedback annotations

Community

Reviews

Be the first to review

Have you used this server?

Share your experience — it helps other developers decide.

How easy was setup?Did it work reliably?How was the documentation?

Frequently Asked Questions

Is io.github.us-all/mlflow safe to use?: io.github.us-all/mlflow has no known CVEs as of the latest MCPpedia security scan. It does not require authentication, so any local process can connect — keep this in mind in shared environments. Licensed under MIT.
How do I install io.github.us-all/mlflow?: io.github.us-all/mlflow supports copy-paste install configs on its MCPpedia page for Claude Desktop, Cursor, and Claude Code. Scroll to the Quick Install section and select your client.
What can io.github.us-all/mlflow do?: io.github.us-all/mlflow provides 10 tools: summarize-experiment, summarize-run, compare-runs, search-tools, get-run and 5 more. See the full tools list on the server page for descriptions and parameters.
What AI clients work with io.github.us-all/mlflow?: io.github.us-all/mlflow is compatible with claude-desktop, cursor, claude-code. It uses stdio and sse and http transport.
Is io.github.us-all/mlflow actively maintained?: io.github.us-all/mlflow is recently maintained — last commit was 48 days ago. It has 1 GitHub stars.

Similar servers

Others in other

View all →

Headroom95

Compress tool outputs, logs, files, and RAG chunks before they reach the LLM. 60-95% fewer tokens, same answers. Library, proxy, MCP server.

67.6k 3

Transport Stdio95

Transport for TMCP using STDIO

197 14

Flare95

The graph based agentic IDE

179 3

app.fojin/fojin-mcp94

Buddhist canon tools: search, passages, cross-canon parallels, dictionaries — all URN-cited.

333 8

MCP Security Weekly

Get CVE alerts and security updates for io.github.us-all/mlflow and similar servers.

Community

Discussion

Start a conversation

Ask a question, share a tip, or report an issue.

Has anyone used this with Cursor?How do you handle auth?Any alternatives?

{ "mcpServers": { "mlflow": { "env": { "MLFLOW_TRACKING_URI": "http://localhost:5000" }, "args": [ "-y", "@us-all/mlflow-mcp" ], "command": "npx" } } }

Frequently Asked Questions

Is io.github.us-all/mlflow safe to use?

io.github.us-all/mlflow has no known CVEs as of the latest MCPpedia security scan. It does not require authentication, so any local process can connect — keep this in mind in shared environments. Licensed under MIT.

How do I install io.github.us-all/mlflow?

io.github.us-all/mlflow supports copy-paste install configs on its MCPpedia page for Claude Desktop, Cursor, and Claude Code. Scroll to the Quick Install section and select your client.

What can io.github.us-all/mlflow do?

io.github.us-all/mlflow provides 10 tools: summarize-experiment, summarize-run, compare-runs, search-tools, get-run and 5 more. See the full tools list on the server page for descriptions and parameters.

What AI clients work with io.github.us-all/mlflow?

io.github.us-all/mlflow is compatible with claude-desktop, cursor, claude-code. It uses stdio and sse and http transport.

Is io.github.us-all/mlflow actively maintained?

io.github.us-all/mlflow is recently maintained — last commit was 48 days ago. It has 1 GitHub stars.