Log inSubmit server
Mlflow MCP Server logo

Mlflow MCP Server

by us-all

MLflow MCP server with tools for experiments, runs, models, traces, assessments, webhooks, and prompt workflows.

InstallRepositoryWebsite
Full README Compare alternatives Embed widget Claim this listing

Install Mlflow MCP Server

Pick your client, then add it in one click or paste the config.

STDIONode.js
~/Library/Application Support/Claude/claude_desktop_config.json
claude_desktop_config.json
{
  "mcpServers": {
    "us-all-mlflow-mcp-server": {
      "command": "npx",
      "args": [
        "-y",
        "@us-all/mlflow-mcp"
      ],
      "env": {
        "MLFLOW_TRACKING_URI": "YOUR_VALUE_HERE",
        "MLFLOW_TRACKING_TOKEN": "YOUR_VALUE_HERE",
        "MLFLOW_TRACKING_USERNAME": "YOUR_VALUE_HERE",
        "MLFLOW_TRACKING_PASSWORD": "YOUR_VALUE_HERE",
        "MLFLOW_EXPERIMENT_ID": "YOUR_VALUE_HERE",
        "MLFLOW_ALLOW_WRITE": "YOUR_VALUE_HERE",
        "MLFLOW_TOOLS": "YOUR_VALUE_HERE",
        "MLFLOW_DISABLE": "YOUR_VALUE_HERE"
      }
    }
  }
}

Settings → Developer → Edit Config, merge this into mcpServers, then fully quit and reopen Claude Desktop.

Values are written into the snippet above so you can paste it as is. They never leave your browser.

Install not yet sandbox-tested— we haven't run this command through our automated sandbox yet. Not a red flag; we're working through the catalog.

Overview

us-all/mlflow-mcp-server MCP server exposes MLflow operations to MCP clients through 82 tools covering experiments, runs, registered models, logged models, traces, assessments, webhooks, and prompt-optimization jobs. It connects to an MLflow tracking URL through the REST API and supports stdio by default or Streamable HTTP when configured. Aggregation tools reduce round-trips, while MCP prompts and resources provide reusable workflows and structured access to MLflow entities. Reach for it when an agent needs broad MLflow 3 coverage, trace investigation, run comparison, or controlled write access.

Use cases

  • Find the best experiment run by a validation metric
  • Compare top runs and identify differing hyperparameters
  • Group failed traces by exception type
  • Inspect trace attachments in Databricks MLflow
  • Promote a selected run to a registered model alias

Key features

  • 82 tools across MLflow experiments, runs, registry, traces, and more
  • MLflow 3 LoggedModel and GenAI trace coverage
  • Aggregation tools for experiment and run summaries
  • Four reusable MCP workflow prompts
  • Six MLflow resource URI patterns
  • stdio and Streamable HTTP transports

Tools62

What Mlflow MCP Server lets your agent do. Expand a tool for its parameters.

Self-reported~310 tokens of context

Security & health

What it can reach and how reliably it runs — from our own checks, not the maintainer’s claims.

ActiveLast checked 1d ago

Recent health check succeeded.

17/18 checks healthy over the last 78d

Supply-chain signal

No high-severity advisories surfaced by our automated scan.

Critical 0High 0Medium 0Low 0

Scanned 11d ago via OSV.dev · @us-all/mlflow-mcp (npm)

Adoption & maintenance

Factual signals from GitHub, npm, and our automated checks — not a rating.

GitHub stars1Stargazers on the source repository.
npm downloads232Package downloads in the last 30 days.
Last commit3mo agoMost recent push to the default branch.
Tools exposed62Callable tools this server registers over MCP.
Directory activity2 viewsConfig copies, upvotes, and views on AllMCPs.

How Mlflow MCP Server works

What us-all/mlflow-mcp-server MCP server does

The us-all/mlflow-mcp-server MCP server exposes MLflow data and operations as MCP tools. Its coverage includes experiments, runs, model registry entities, MLflow 3 LoggedModel records, traces, assessments, webhooks, and prompt-optimization jobs. The package also provides four workflow prompts: debug-failed-traces, promote-best-run, compare-top-runs, and annotate-trace-quality.

The server is suited to agent-driven experiment analysis and MLflow 3 trace debugging. Example tasks include finding the best run by a metric, comparing hyperparameters across top runs, inspecting failed traces, reviewing feedback annotations, and following a registered model back to its source run.

How it works

The server uses MLFLOW_TRACKING_URI to connect to an OSS MLflow deployment or a Databricks workspace. Bearer-token and basic authentication options are available through environment variables. It starts with stdio transport; setting MCP_TRANSPORT=http enables Streamable HTTP with /mcp for JSON-RPC requests and /health for liveness checks.

summary-experiment combines experiment details, top runs, and metric statistics in one response. summarize-run reduces repeated metric-history fields in large responses. Several read tools support extractFields, allowing a caller to request only selected response fields. The server also exposes six mlflow:// resource URI patterns for runs, experiments, artifacts, registered model versions, and traces.

Setup and configuration

Install it through the npm package with npx -y @us-all/mlflow-mcp, run the published Docker image, or build from source with pnpm. Claude Desktop and Claude Code examples are provided in the project documentation.

MLFLOW_TRACKING_URI is required. Use MLFLOW_TRACKING_TOKEN for a bearer token such as a Databricks personal access token, or provide MLFLOW_TRACKING_USERNAME and MLFLOW_TRACKING_PASSWORD for basic authentication. MLFLOW_EXPERIMENT_ID can supply a default experiment context.

Writes are disabled by default. Set MLFLOW_ALLOW_WRITE=true before using create, update, delete, restore, logging, registration, trace, assessment, webhook, or prompt-optimization mutations. For HTTP mode, configure MCP_HTTP_TOKEN unless authentication is intentionally skipped behind a trusted reverse proxy.

Tools and capabilities

The us-all/mlflow-mcp-server MCP server groups tools into eight configurable categories: experiments, runs, registry, logged models, traces, assessments, webhooks, and prompts. MLFLOW_TOOLS allows an allowlist of categories, while MLFLOW_DISABLE provides a denylist when no allowlist is set.

Trace tools can search and retrieve MLflow 3 traces, and Databricks deployments additionally support listing and retrieving trace attachments. Run and experiment tools support metric, parameter, tag, artifact, and history operations. Registry tools cover registered models and model versions. A search-tools meta-tool helps locate available tools, and compare-runs can render a comparison card for supported ChatGPT clients while returning JSON content to Claude clients.

Limitations and notes

Trace search limits each page to 500 results. Larger searches require following nextPageToken; the cap does not limit the total paginated result set. Trace attachments are Databricks-only because OSS MLflow returns 404 for those routes.

The documentation notes that bearer and basic authentication paths have not yet been validated against a live Databricks deployment. OSS MLflow 3.12 is supported with bearer authentication optional. HTTP mode requires a bearer token by default, and the server binds to 127.0.0.1 on port 3000 unless configured otherwise.

Read the full README View source on GitHub

Reviews

No reviews yet — be the first to share how it worked for you.

Frequently Asked Questions about Mlflow MCP Server

us-all/mlflow-mcp-server is an MCP server that connects AI clients to an MLflow tracking server or Databricks MLflow. Its main tools cover experiments, runs, registered models, logged models, traces, assessments, webhooks, and prompt-optimization jobs, with aggregation tools for experiment and run summaries.

Install it with npx, Docker, or from source. Use `npx -y @us-all/mlflow-mcp` in an MCP client configuration, run the published GitHub Container Registry image, or clone the repository and build it with pnpm.

Set `MLFLOW_TRACKING_URI` to the MLflow tracking URL. You can optionally add a bearer token with `MLFLOW_TRACKING_TOKEN`, or use `MLFLOW_TRACKING_USERNAME` and `MLFLOW_TRACKING_PASSWORD` for basic authentication.

Set `MLFLOW_ALLOW_WRITE=true` to enable mutations. Without that setting, write operations are blocked, including experiment changes, run logging, model registry updates, trace and assessment writes, webhook changes, and prompt-optimization writes.

Yes, it works with Claude Desktop through the documented stdio configuration. Set the `command` to `npx`, pass `-y` and `@us-all/mlflow-mcp`, and provide `MLFLOW_TRACKING_URI` in the client environment.

Related MCP servers

All in Other Tools and Integrations All alternatives
Add a badge to your READMEShow it’s listed — live SVG, Markdown or HTML.

AllMCPs Directory Badge

Full Badge Customizer

Showcase your server listing on GitHub or your project documentation. Embed this dynamic SVG badge to highlight official listing status and live engagement.

Badge Style:
Live Dynamic SVG PreviewMlflow MCP Server AllMCPs Directory Badge
Markdown (GitHub README)
[![AllMCPs](https://allmcps.com/api/badge/us-all-mlflow-mcp-server?style=directory)](https://allmcps.com/mcp/us-all-mlflow-mcp-server)
HTML Embed
<a href="https://allmcps.com/mcp/us-all-mlflow-mcp-server"><img src="https://allmcps.com/api/badge/us-all-mlflow-mcp-server?style=directory" alt="Mlflow MCP Server on AllMCPs" /></a>