---
title: "MLflow MCP Server: review, setup & limitations · Undominated.ai"
canonical: https://undominated.ai/mcp-servers/mlflow-mcp/
description: "Ships inside the mlflow package and exposes trace search, feedback and assessment logging, and optionally experiment, run, model and deployment commands, to an MCP client."
---

# MLflow MCP Server: review, setup & limitations · Undominated.ai

> Ships inside the mlflow package and exposes trace search, feedback and assessment logging, and optionally experiment, run, model and deployment commands, to an MCP client.

[← Explore all mcp servers](/mcp-servers/)

LLM OBSERVABILITY / MLflow

# MLflow MCP Server

Ships inside the mlflow package and exposes trace search, feedback and assessment logging, and optionally experiment, run, model and deployment commands, to an MCP client.

 [See setup guidance ↓](#setup)[Original source ↗](https://github.com/mlflow/mlflow/tree/b033c768636ed945de47356a7f14e922ad2d9674/mlflow/mcp)

SOURCE REVIEW

 Reviewed 2026-10-13
 Evidence 5 linked sources
 Publisher MLflow
 Licence [Apache-2.0 ↗](https://github.com/mlflow/mlflow/blob/b033c768636ed945de47356a7f14e922ad2d9674/LICENSE.txt)
 Revision b033c768636e
 [Read what was—and wasn’t—checked ↓](#review)

“Connect AI assistants and coding tools to MLflow using the Model Context Protocol (MCP). Search traces, analyze performance, log feedback, and more from Claude Code, Codex, Cursor, and Gemini CLI.”

 [MLflow · upstream description ↗](https://github.com/mlflow/mlflow/blob/b033c768636ed945de47356a7f14e922ad2d9674/docs/docs/genai/mcp/index.mdx) Our analysis follows below.

01 / THE REASONING

## Why this made the selection.

 - The server is part of MLflow itself at this commit (mlflow/mcp/server.py and cli.py), installed with the mcp extra, and the documentation page at the same commit gives configuration for VS Code, Cursor and Claude Code.
- The documented tools include log_feedback, log_expectation and assessment updates on traces, and server.py maps MLFLOW_MCP_TOOLS to tool categories: genai (default: traces, scorers, experiments, runs), ml (experiments, runs, models, deployments) or all.

### A good fit for

 - Querying and annotating traces of an LLM application that is already instrumented with MLflow Tracing
- Finding failed or slow traces in an experiment with search_traces and filter strings such as status='ERROR'

### Weigh up before choosing

 - The documentation marks the feature experimental and requires MLflow 3.5.1 or newer. delete_traces and delete_assessment remove data from the tracking server.
- mlflow/mcp/cli.py decorates mlflow mcp run with record_usage_event(McpRunEvent), so starting the server records an MLflow telemetry usage event; MLflow's telemetry settings were not reviewed here.
- server.py builds tools from MLflow CLI commands; the full tool list for the ml and all categories was not enumerated. Nothing was installed or run.

02 / THE REVIEW RECORD

## What we actually inspected.

Source review has boundaries. A clear record is more useful than a “safe” badge.

### Material inspected

 - docs/docs/genai/mcp/index.mdx at b033c768636ed945de47356a7f14e922ad2d9674
- mlflow/mcp/server.py and mlflow/mcp/cli.py at the same commit
- LICENSE.txt and pyproject.toml at the same commit

### Our findings

 - run_server builds a FastMCP server named Mlflow MCP and calls mcp.run(show_banner=False); the documented client configurations start it as a command (uv run --with mlflow[mcp]>=3.5.1 mlflow mcp run).
- pyproject.toml defines the mcp extra as fastmcp<4,>=2.7.0 and click!=8.3.0. LICENSE.txt is Apache 2.0, Copyright 2018 Databricks, Inc.
- For Databricks, the documentation sets the tracking URI to databricks with DATABRICKS_HOST and DATABRICKS_TOKEN.

### Not established by this review

 - pip or uv install
- Any call to an MLflow tracking server
- The ml and all tool categories

The review applies to the material and revision named here. A newer upstream release can change its behavior.

03 / PUT IT TO WORK

## Connect a server deliberately.

[Upstream setup instructions ↗](https://github.com/mlflow/mlflow/blob/b033c768636ed945de47356a7f14e922ad2d9674/docs/docs/genai/mcp/index.mdx)

DOCUMENTED COMMAND

 pip install 'mlflow[mcp]>=3.5.1' Copy command ↗

Copying does not execute this command. It may retrieve a newer version than the reviewed source.

 - Install MLflow with the mcp extra as above; the documentation's client blocks instead run it through uv. It was not run.
- Set MLFLOW_TRACKING_URI to your tracking server, and MLFLOW_MCP_TOOLS to limit tool categories.

### Before you start

 - Python with pip or uv
- MLflow 3.5.1 or newer
- An MLflow tracking server or Databricks workspace

### Documented configuration example

Use the client and authentication context described in the setup guidance. Configuration formats vary between hosts.

 {
 "mcpServers": {
 "mlflow-mcp": {
 "command": "uv",
 "args": [
 "run",
 "--with",
 "mlflow[mcp]>=3.5.1",
 "mlflow",
 "mcp",
 "run"
 ],
 "env": {
 "MLFLOW_TRACKING_URI": "<MLFLOW_TRACKING_URI>"
 }
 }
 }
} Copy configuration ↗

### Compatibility

VS Code · Cursor · Claude Code · Codex · Gemini CLI

### Implementation

Python

### Transports

stdio

### Local process with MLflow tracking-server access

 - Searches and reads traces, assessments and tags at MLFLOW_TRACKING_URI
- Logs feedback and expectations, sets tags, and deletes traces and assessments

### Cost model

Apache-2.0 source. A tracking server or Databricks workspace carries its own costs; no price was reviewed.

04 / FOLLOW THE EVIDENCE

## The source trail.

Our notes are separate from the original resource. Check upstream before adopting a new version.

 - [MLflow MCP Server documentation ↗](https://github.com/mlflow/mlflow/blob/b033c768636ed945de47356a7f14e922ad2d9674/docs/docs/genai/mcp/index.mdx) Checked 2026-10-13 https://github.com/mlflow/mlflow/blob/b033c768636ed945de47356a7f14e922ad2d9674/docs/docs/genai/mcp/index.mdx Supports: Experimental status, Installation, Client configuration, Tools, Tool categories
- [MLflow MCP server.py ↗](https://github.com/mlflow/mlflow/blob/b033c768636ed945de47356a7f14e922ad2d9674/mlflow/mcp/server.py) Checked 2026-10-13 https://github.com/mlflow/mlflow/blob/b033c768636ed945de47356a7f14e922ad2d9674/mlflow/mcp/server.py Supports: Tool category mapping, FastMCP server run
- [MLflow MCP cli.py ↗](https://github.com/mlflow/mlflow/blob/b033c768636ed945de47356a7f14e922ad2d9674/mlflow/mcp/cli.py) Checked 2026-10-13 https://github.com/mlflow/mlflow/blob/b033c768636ed945de47356a7f14e922ad2d9674/mlflow/mcp/cli.py Supports: mlflow mcp run command, Usage-event decorator
- [MLflow LICENSE.txt ↗](https://github.com/mlflow/mlflow/blob/b033c768636ed945de47356a7f14e922ad2d9674/LICENSE.txt) Checked 2026-10-13 https://github.com/mlflow/mlflow/blob/b033c768636ed945de47356a7f14e922ad2d9674/LICENSE.txt Supports: Apache License 2.0, Copyright 2018 Databricks, Inc.
- [MLflow pyproject.toml ↗](https://github.com/mlflow/mlflow/blob/b033c768636ed945de47356a7f14e922ad2d9674/pyproject.toml) Checked 2026-10-13 https://github.com/mlflow/mlflow/blob/b033c768636ed945de47356a7f14e922ad2d9674/pyproject.toml Supports: mcp extra dependencies

KEEP COMPARING

## Other approaches to consider.

Related by category or shared topics. These are alternatives to inspect, not a measured quality order.

 [### Helicone MCP Server ↗ Connects an assistant to Helicone request logs and sessions, and can send new LLM requests through the Helicone AI Gateway. It runs locally over stdio via the published npm package with a Helicone API key.](/mcp-servers/helicone/)[### OpenTelemetry MCP Server ↗ Queries LLM application traces in Jaeger, Grafana Tempo or Traceloop, with tools that aggregate token usage by model and find slow, token-heavy or failing traces.](/mcp-servers/opentelemetry-mcp/)[### Opik MCP Server ↗ Reads and scores Opik traces, experiments, datasets and prompts from an MCP client. Comet hosts it for Opik Cloud; self-hosted and open-source Opik run the same package locally over stdio.](/mcp-servers/opik-mcp/)

 [AI Tools ↗](/tools/)[Skills ↗](/skills/)[Agents ↗](/agents/)[MCP Servers ↗](/mcp-servers/)[Workflows ↗](/workflows/)

## Continue your investigation

 - [Inspect resource evidence](/tools/)
- [Choose a host](/agents/)
- [Inspect reusable workflows](/skills/)
- [Use Undominated data](/api/)
