io.github.us-all/mlflow

io.github.us-all/mlflowv1.12.7Other

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

In-path gate · all MCP tools

Using io.github.us-all/mlflow in Claude, Cursor, Gemini CLI, Cline, or Zed?

MCP tool contracts can change remotely with no version bump. The mcpindex gate pins each contract and HOLDs the call when it drifts-before your agent acts. Zero credentials. This is not the package install for this server itself (use Install this server for that).

Install the mcpindex gate (one command)

Rewrites your MCP host config so each server launches behind the gate. Inspect first: curl -fsSL https://mcpindex.ai/install.sh | less

uv tool install mcpindex-gate && mcpindex-config-wire

Auditable install path →Watch it hold a drift →

Trust verdict · v1 advisory · method

REVIEWstatus: PARTIALfresh until 2026-08-12 11:18 UTC

screened 2026-07-04tier: scannedgranularity: description-levelsource: registry

Semantic screen found no manipulation pattern in the description. Conformance probe not yet run.

mcpindex.integrity.descriptionpassINFO

evidence“No malicious instructions found”via static_description

Limits of this verdict

- Semantic screen only - the deterministic conformance probe has not run on this server
- Confidence is reported but not yet calibrated (v1)
- Screen reads the tool description, not the live behavior
- advisory
- registry description only no input schema
- screen model 8b
- Still current: the description we screened is unchanged, re-checked against the registry

Semantic screen: an LLM judge reads the tool description for hidden instructions (status PARTIAL). A pass means the description is not lying, not that the tool is safe: a high-capability tool with an honest description still warrants caution. The deterministic conformance probe has not been run on this server yet, so the screen here is semantic-only. Posture: advisory. Confidences are reported but not yet calibrated (calibrated=false at v1). Full verdict history is not shown on this page.

Own this server? Screen its description →

That verdict was true at screening time (snapshot 2026-08-05).

Contracts can change after screening, with no version bump. The gate pins io.github.us-all/mlflow’s tool contracts on first sight and holds any silent change before your agent acts - the check that keeps being true on Tuesday.

See your first HOLD in 2 minutes →

Embed this badge

A live verdict badge for your README or listing. It reflects the current screen, links back here, and updates when the verdict does.

Markdown

[![mcpindex](https://mcpindex.ai/api/v1/badge/io-github-us-all-mlflow)](https://mcpindex.ai/server/io-github-us-all-mlflow)

HTML

<a href="https://mcpindex.ai/server/io-github-us-all-mlflow"><img src="https://mcpindex.ai/api/v1/badge/io-github-us-all-mlflow" alt="mcpindex verdict" height="20" /></a>

Environment variables

MLFLOW_TRACKING_URI

required

MLflow tracking server URI (e.g. http://localhost:5050, https://mlflow.example.com).

MLFLOW_TRACKING_TOKEN

secret

Bearer token for authenticated MLflow servers (e.g. Databricks).

MLFLOW_TRACKING_USERNAME

Basic-auth username (alternative to token).

MLFLOW_TRACKING_PASSWORD

secret

Basic-auth password (alternative to token).

MLFLOW_EXPERIMENT_ID

Default experiment ID for run-creation tools.

MLFLOW_TOOLS

Comma-separated category allowlist. Default: all categories enabled.

MLFLOW_DISABLE

Comma-separated category disablelist.

MLFLOW_ALLOW_WRITE

Set to 'true' to enable write/destructive tools. Default read-only.

MCP quality score · maturity, not trust · methodology

freshness

completeness

installability

documentation

stability

Alternatives in Other

ConnectMachine

ai.connectmachine/connectmachine

Manage your ConnectMachine contacts, networks, events, and digital business cards.

Yarr MCP

ai.dinglebear/yarr

Self-hosted media fleet operations across Sonarr, Radarr, Plex, and related apps over MCP and CLI.

io.github.usekaneo/kaneo

Official MCP server for Kaneo: manage tasks, projects, and labels from Claude and other MCP clients

Install this server

Claude Desktop (claude_desktop_config.json)

{
  "mcpServers": {
    "mlflow": {
      "command": "npx",
      "args": [
        "-y",
        "--",
        "@us-all/mlflow-mcp"
      ],
      "env": {
        "MLFLOW_TRACKING_URI": "<mlflow_tracking_uri>",
        "MLFLOW_TRACKING_TOKEN": "<your-mlflow_tracking_token>",
        "MLFLOW_TRACKING_USERNAME": "<mlflow_tracking_username>",
        "MLFLOW_TRACKING_PASSWORD": "<your-mlflow_tracking_password>",
        "MLFLOW_EXPERIMENT_ID": "<mlflow_experiment_id>",
        "MLFLOW_TOOLS": "<mlflow_tools>",
        "MLFLOW_DISABLE": "<mlflow_disable>",
        "MLFLOW_ALLOW_WRITE": "false"
      }
    }
  }
}

Cursor (.cursor/mcp.json)

{
  "mcpServers": {
    "mlflow": {
      "command": "npx",
      "args": [
        "-y",
        "--",
        "@us-all/mlflow-mcp"
      ],
      "env": {
        "MLFLOW_TRACKING_URI": "<mlflow_tracking_uri>",
        "MLFLOW_TRACKING_TOKEN": "<your-mlflow_tracking_token>",
        "MLFLOW_TRACKING_USERNAME": "<mlflow_tracking_username>",
        "MLFLOW_TRACKING_PASSWORD": "<your-mlflow_tracking_password>",
        "MLFLOW_EXPERIMENT_ID": "<mlflow_experiment_id>",
        "MLFLOW_TOOLS": "<mlflow_tools>",
        "MLFLOW_DISABLE": "<mlflow_disable>",
        "MLFLOW_ALLOW_WRITE": "false"
      }
    }
  }
}

Cline (cline_mcp_settings.json)

npx -y -- @us-all/mlflow-mcp

Claude Code (claude mcp add)

claude mcp add --scope user mlflow -- npx -y -- @us-all/mlflow-mcp

Gemini CLI (gemini mcp add)

gemini mcp add -s user mlflow npx -y -- @us-all/mlflow-mcp

Verdict API

curl -s mcpindex.ai/api/v1/trust/server/io-github-us-all-mlflow

Free-tier verdict as JSON: decision + dimensions + severity. Call it from your agent before it invokes a tool it just discovered.

Details

version: v1.12.7
category: Other
verdict expires: 2026-08-12
quality: 84 / 100
operator: us-all

Listing

Listed from the official MCP registry. Unclaimed by its maintainer. Maintainer? Email us →

Provenance

Each verdict is bound to a hash of the exact description it judged, so a re-crawl that changes the text produces a new record rather than silently inheriting this one. Verdict history is hash-chained and anchored to Bitcoin via OpenTimestamps (latest confirmed at block 960,824). Verify it yourself.

Links

Repository →