Other · Local MCP server

Mlflow

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

What the MCP Registry states

The entry as published to the official MCP Registry (read 2026-10-04), latest version.

Registry name
io.github.us-all/mlflow
Version
1.12.7
Status
Active
Category
other
Transport
stdio (local process)
Package
npm
Published
2026-06-19
Updated
2026-06-19
Publisher
us-all (GitHub) · 8 servers with pages here
Namespace
Namespace verified by the MCP Registry via GitHub (github.com/us-all) · how
Repository
github.com/us-all/mlflow-mcp-server
Source
Registry API entry

Packages

RegistryPackageVersionTransportEnvironment variables
npm@us-all/mlflow-mcp1.12.7stdioMLFLOW_TRACKING_URI (required), MLFLOW_TRACKING_TOKEN (secret), MLFLOW_TRACKING_USERNAME, MLFLOW_TRACKING_PASSWORD (secret), MLFLOW_EXPERIMENT_ID, MLFLOW_TOOLS, MLFLOW_DISABLE, MLFLOW_ALLOW_WRITE

How to connect Mlflow

Mlflow runs locally from a Node.js package published to the npm registry: @us-all/mlflow-mcp version 1.12.7. It speaks MCP over stdio, so the client starts it as a program and talks to it through standard input and output. It needs Node.js; clients usually start it with npx - the usual command is npx -y @us-all/mlflow-mcp@1.12.7. It reads these environment variables: MLFLOW_TRACKING_URI (required), MLFLOW_TRACKING_TOKEN (secret), MLFLOW_TRACKING_USERNAME, MLFLOW_TRACKING_PASSWORD (secret), MLFLOW_EXPERIMENT_ID, MLFLOW_TOOLS, MLFLOW_DISABLE and MLFLOW_ALLOW_WRITE; set them in the client's configuration for this server.

In the mcpServers JSON format that many desktop and editor MCP clients read, the entry looks like this (placeholders in angle brackets):

{
  "mcpServers": {
    "mlflow": {
      "command": "npx",
      "args": [
        "-y",
        "@us-all/mlflow-mcp@1.12.7"
      ],
      "env": {
        "MLFLOW_TRACKING_URI": "<value>",
        "MLFLOW_TRACKING_TOKEN": "<secret>",
        "MLFLOW_TRACKING_USERNAME": "<value>",
        "MLFLOW_TRACKING_PASSWORD": "<secret>",
        "MLFLOW_EXPERIMENT_ID": "<value>",
        "MLFLOW_TOOLS": "<value>",
        "MLFLOW_DISABLE": "<value>",
        "MLFLOW_ALLOW_WRITE": "<value>"
      }
    }
  }
}

Derived from the registry entry, not tested here. What the server does, and on what terms, is set by its publisher; check its repository or website before giving it access to your accounts or files. How to add an MCP server to an assistant · Before you connect

More from us-all (GitHub)

All 8 →
ServerRunsEndpoint or package
AirflowAirflow MCP - list DAGs/runs/task instances, tail logs, trigger and clear (write-gated)Local · stdionpm: @us-all/airflow-mcp
AndroidAndroid MCP - ADB-based device, apps, UI, logcat, emulator, files, system, debug.Local · stdionpm: @us-all/android-mcp
DatadogDatadog MCP - 165 tools for metrics, monitors, logs, APM, RUM, incidents, CI/CD, fleet.Local · stdionpm: @us-all/datadog-mcp
DbtDbt MCP - manifest/run_results/sources/catalog parsing + DQ result tables (BigQuery/Postgres)Local · stdionpm: @us-all/dbt-mcp
Google DriveGoogle Drive + Workspace MCP - Docs, Sheets, Slides, Shared Drives, Labels, Approvals, DWD.Local · stdionpm: @us-all/google-drive-mcp
OpenmetadataOpenMetadata MCP - metadata, lineage, search, data quality, OM 1.12+ Data Contracts.Local · stdionpm: @us-all/openmetadata-mcp
UnifiUniFi semantic-analysis MCP - fleet health, anomaly detection, cross-site analytics.Local · stdionpm: @us-all/unifi-mcp

More other servers

All 8,395 →
ServerRunsEndpoint or package
MixpanelQuery Mixpanel events, funnels, retention, segmentation and insights (JQL).Remote · HTTPLive check: ✓ handshakemixpanel.usefulapi.io
Mixpanel MCPQuery Mixpanel events, funnels, retention, cohorts, and user profiles.Local · stdionpm: @mrfentmen/mixpanel-mcp
Mixx Dj MCPFastMCP server for Mixxx DJ software control via OSC protocol.Local · stdioMCP Bundle (.mcpb): sandraschi/mixx-dj-mcp/releases/download/v0.2.0/
Mlb MCPTeams, schedules, and standings from the official MLB Stats API. No key required.Local · stdionpm: mlb-mcp
Mlua SwarmMCP server for mlua-swarm: engine that compiles flow.ir Blueprints and dispatches agent steps.Local · stdioOCI image (Docker): ghcr.io/ynishi/mse:0.29.0
MMW Managed Memory WorkspaceUltra-fast persistent memory workspace with tenant isolation and cross-model continuity.Remote · HTTPLive check: sign-in requiredmcp.mmwhub.tech
MnemaLocal-first, formally verified memory for AI agents: consult/learn/related/list over MCP.Local · stdioMCP Bundle (.mcpb): Zimac-AI/mnema/releases/download/v0.2.0/mnema-0.
Mneme Decision MCPLocal MCP server for architectural decisions, traceability, and non-authoritative proposals.Local · stdioPyPI: mneme-hq