AUTOMATIONSWITCH
CommunityAI / ML

MLflow MCP

by kkruglik (community)

MLflow MCP server for ML experiment tracking. Query experiments, runs, registered models, and model versions with advanced filtering. 10 GitHub stars and 30 commits on main in the last 30 days. Tier 2 by stars.

10·6 tools·Released APR 2026·MIT
pip install mlflow-mcp
Share:

MLflow MCP server for ML experiment tracking. Query experiments, runs, registered models, and model versions from inside agents. 10 stars and 30 commits on main in the last 30 days. Tier 2.

Reviewed by M. Nouriel · MAY 2026

INSTALL THIS SERVER

Requires authenticationMLFLOW_TRACKING_URI environment variable pointing at the MLflow tracking server. Bearer token authentication via MLFLOW_TRACKING_TOKEN where the server requires it.
{ "mcpServers": { "mlflow": { "command": "python", "args": [ "-m", "mlflow_mcp" ], "env": { "MLFLOW_TRACKING_URI": "https://your-mlflow.example.com", "MLFLOW_TRACKING_TOKEN": "YOUR_TOKEN" } } } }
PrereqPyPI: `mlflow-mcp`. Set MLFLOW_TRACKING_URI to your tracking server. Bearer token via MLFLOW_TRACKING_TOKEN where required. Path: ~/Library/Application Support/Claude/claude_desktop_config.json (macOS).
{ "mcpServers": { "mlflow": { "command": "python", "args": [ "-m", "mlflow_mcp" ], "env": { "MLFLOW_TRACKING_URI": "https://your-mlflow.example.com", "MLFLOW_TRACKING_TOKEN": "YOUR_TOKEN" } } } }
{ "mcpServers": { "mlflow": { "command": "python", "args": [ "-m", "mlflow_mcp" ], "env": { "MLFLOW_TRACKING_URI": "https://your-mlflow.example.com", "MLFLOW_TRACKING_TOKEN": "YOUR_TOKEN" } } } }
{ "mcpServers": { "mlflow": { "command": "python", "args": [ "-m", "mlflow_mcp" ], "env": { "MLFLOW_TRACKING_URI": "https://your-mlflow.example.com", "MLFLOW_TRACKING_TOKEN": "YOUR_TOKEN" } } } }
{ "mcpServers": { "mlflow": { "command": "python", "args": [ "-m", "mlflow_mcp" ], "env": { "MLFLOW_TRACKING_URI": "https://your-mlflow.example.com", "MLFLOW_TRACKING_TOKEN": "YOUR_TOKEN" } } } }

6 TOOLS AVAILABLE

list_experiments
List MLflow experiments visible to the connection
Read
list_runs
List runs within an experiment with filters
Read
compare_runs
Compare metrics across multiple runs
Read
list_registered_models
List registered models in the MLflow registry
Read
list_model_versions
List versions of a registered model
Read
get_run_metrics
Retrieve metrics, params, and artifacts for a run
Read

OUR ASSESSMENT

Strengths
  • 30 commits on main in the last 30 days. Top-tier cadence.
  • MIT license.
  • MLflow itself is a mature platform.
  • Direct access to experiments, runs, and registered models.
  • Active community development.
Weaknesses
  • 10 GitHub stars indicates very early adoption.
  • Tier 2 designation reflects MCP maturity, not platform maturity.
  • Tool surface is read-heavy; model registration requires the MLflow CLI/SDK directly.
Security Notes

MLFLOW_TRACKING_TOKEN carries the connecting user permission. For self-hosted MLflow, use a service-account user scoped to the agent flow. Read-only tool surface keeps blast radius small.

Best For

ML teams running MLflow self-hosted or MLflow-on-Databricks; agents that triage experiment failures or compare run metrics; mlops engineers adopting agent-driven model registry operations.

TECHNICAL DETAILS

Language
python
Transport
stdio
Clients
Claude DesktopClaude CodeCursorVS CodeWindsurf
License
MIT
GitHub
npm
mlflow-mcp
Last Release
mlflow-mcp (PyPI latest)MAY 6, 2026
First Released
APR 1, 2026

ADOPTION METRICS

// GitHub Stars
10

// Reading this10 stars on kkruglik/mlflow-mcp. 30 commits on main in the last 30 days, top-tier cadence.

// Popularity Rank
#12
Globally · #12 in AI / ML

// Reading thisPairs with W&B, Arize Phoenix, Pinecone, Qdrant, Cognee in ai-ml. MLflow covers the open-source experiment-tracking standard uniquely.

SOURCES & VERIFICATION

We don't take any single directory's word for it. Before scoring, we cross-reference 3 public MCP sources, install the server ourselves against the clients we cover, and record when we last re-verified.

01
Discovered
Manual submission
First indexed MAY 6, 2026
02
Cross-referenced
3 directories
PulseMCP, MCP.so, Glama
03
Verified against
Claude Desktop
Installed and tested across clients
04
Last re-checked
MAY 6, 2026
Weekly re-verification
// How other directories see it

The same server, 3 different lenses. We reconcile these signals into our editorial score, which is why our number sometimes diverges from a directory-aggregate star count.

SourceTheir ratingTheir star countTheir downloadsLast synced
AutomationSwitch This page3.9editorial10MAY 6, 2026
PulseMCP— unratedunavailableunavailableMAY 6, 2026
MCP.so— unratedunavailableunavailableMAY 6, 2026
Glama— unratedunavailableunavailableMAY 6, 2026

// Counts are directory-reported; we don't adjust them. Discrepancies usually come from different snapshot times or star-caching.

OTHER AI / ML MCP SERVERS

Community4.6

Cognee MCP

topoteretes

Knowledge graph plus vector memory engine for AI agents, exposed as an MCP server with V2 session-aware memory tools (remember, recall, forget, improve) and classic V1 ingestion pipelines (cognify, codify). Three transports: stdio, SSE, Streamable HTTP. 16,965 GitHub stars, Apache-2.0.

8 tools16,997
Community4.6

Codebase Memory MCP

DeusData

High-performance code intelligence MCP server for AI coding agents. Indexes a codebase into a queryable knowledge graph in milliseconds, with 14 MCP tools spanning structural search, call-chain tracing, impact analysis, dead-code detection, and Cypher queries. Single static C binary, 66 languages via tree-sitter, zero runtime dependencies.

9 tools2,021
Vendor4.5

Arize Phoenix MCP

Arize AI

LLM observability platform exposing prompts, projects, traces, spans, sessions, datasets, and experiments through MCP. Published to npm as @arizeai/phoenix-mcp, current 4.0.8 (2026-04-29). 9,496 stars on parent monorepo, Elastic License 2.0.

8 tools9,496
Vendor4.5

Qdrant MCP Server

Qdrant

Official Qdrant vector database MCP server. Acts as a semantic memory layer on top of Qdrant: store information with metadata, retrieve via similarity search. Two tools, very small surface area, exceptionally maintained by the Qdrant team. Configurable embedding provider (fastembed default), supports remote and local Qdrant clusters.

2 tools1,373
Official4.4

Amazon Bedrock AgentCore MCP

AWS Labs

Official AWS Labs MCP server for Amazon Bedrock AgentCore: agent runtime, memory, gateway, identity, and observability. Tools fetch curated AgentCore documentation and surface deployment guides for runtime, memory, and gateway resources. Apache-2.0 within awslabs/mcp monorepo (8,924 parent stars).

5 tools8,924
Official4.3

Vapi MCP

Vapi.ai

Vapi.ai voice AI server SDK with MCP server module. Manage voice assistants, trigger outbound calls, and inspect call transcripts. 118 GitHub stars and 14 commits on main in the last 30 days.

6 tools118
// Get in touch

DISCUSS YOUR
MCP REQUIREMENTS.

Evaluating a server, scoping an internal deployment, or working out whether MCP is the right fit at all. Start the conversation and we will point you at the right piece of the ecosystem.

Discuss Your MCP Requirements →