MCP Tools Directory
← Browse integrations

Developer tools

io.github.us-all/mlflow

Free account · sign-in required

Contact io.github.us-all/mlflow

Loading secure sign-in…

Tools for autonomous AI agents

About this integration

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

Transport
stdio
Authentication
none
Initial setup
none
Runtime
unattended
Evidence
documented
Version
1.12.7
Package
@us-all/mlflow-mcp
Last compatibility test
Not independently tested

Connect your agent

@us-all/mlflow-mcp

Publisher README and package manifest reviewed from pinned captures. The package and integration endpoint were not executed or independently security-audited.

Capabilities: Query MLflow experiments and runs, Inspect models and traces, Perform opt-in MLflow write operations

Connected profiles

Additional details

Registry identifier

io.github.us-all/mlflow

Source ↗ · Checked 2026-09-17
Published version

1.12.7

Source ↗ · Checked 2026-09-17
Metadata license

CC0-1.0; package licenses are separate

Source ↗ · Checked 2026-09-17
Package ecosystem

npm

Source ↗ · Checked 2026-09-17
Required configuration names

MLFLOW_TRACKING_URI

Source ↗ · Checked 2026-09-17
Source artifact

@us-all/mlflow-mcp

Source ↗ · Checked 2026-09-20
Source manifest version

1.12.7

Source ↗ · Checked 2026-09-20
Unattended configuration

The README states that stdio is the default transport.

Source ↗ · Checked 2026-09-20
Authentication and prerequisites

An unauthenticated local MLflow tracking URI is supported; bearer-token and basic-auth fields are optional for protected deployments.

Source ↗ · Checked 2026-09-20
Connection configuration

Configure the MCP client to launch @us-all/mlflow-mcp with npx and a tracking URI.

Source ↗ · Checked 2026-09-20
Review scope

Publisher documentation reviewed; package and integration endpoint not executed or independently security-audited.

Source ↗ · Checked 2026-09-20