get_experimentLABSCO SUMMARY
Experiment history and the registry, answerable in a sentence.
The read half covers the question people actually have — which run, what did it score, what is registered — without opening the MLflow UI. The write half reaches into the registry: creating versions from a run's artifacts, moving aliases, and deleting models, which is promotion, not just bookkeeping.
What it is
An MCP server exposing MLflow experiment tracking and model registry operations to an MCP client, published on PyPI as mlflow-mcp-server.
What you get
- Experiments fetched by ID or by name, and searched with name matching and pagination
- A run's full detail — metrics, parameters, tags, and whether it is a parent, child or standalone run
- Runs listed for an experiment with pagination, so a long-running sweep is readable
- Registered models searched and listed, with model versions browsed and filtered
- New registered models created with description and tags, and new versions created from a run's artifacts
- Registered models renamed, and versions deleted
- Aliases assigned to a model version, which is how a stage pointer gets moved
- Registered models deleted when they should no longer exist
Requirements
A reachable MLflow tracking server, set through MLFLOW_TRACKING_URI. It runs with uvx mlflow_mcp_server, so no clone is needed. Whatever authentication your tracking server enforces still applies.
Setup effort
One command — uvx mlflow_mcp_server
USE CASES
01
Finding out which run actually won
List the runs for the experiment and read the metrics on the candidates rather than squinting at a chart.
02
Locating an experiment someone else set up
Search by name, or fetch it directly by name or ID when you know it.
03
Promoting a run to the registry
Create the registered model if it does not exist, then create a version from that run's artifacts.
04
Pointing production at a different version
Set the alias on the version you want serving, so consumers follow the pointer rather than a hardcoded number.
05
Auditing what is registered
List the registered models and browse their versions to see what is still live and what was abandoned.
06
Tidying the registry
Rename models whose names no longer describe them, and delete the versions and models nothing depends on.
13 tools
Listed in project docs. Your client may show a different list.
get_experiment_by_namesearch_experimentsget_runget_experiment_runsget_registered_modelsget_model_versionscreate_registered_modelcreate_model_versionrename_registered_modelset_registered_model_aliasdelete_registered_modeldelete_model_versionBEFORE YOU INSTALL
What to know first
Tools you get
13 tools named in the project's documentation.
Requires
- uvx on PATH
- Python 3.11+
Where it runs
All 3 documented clients run the server on your machine.
INSTALLATION
Connect your client
Server setup
TERMINAL
uvx mlflow_mcp_serverMCP Clients
Claude Desktop, Cursor
JSON
{
"mcpServers": {
"mlflow": {
"command": "uvx",
"args": [
"mlflow_mcp_server"
],
"env": {
"MLFLOW_TRACKING_URI": "http://localhost:5000"
}
}
}
}OpenCode
OPENCODE · JSON
{
"$schema": "https://opencode.ai/config.json",
"mcp": {
"mlflow": {
"type": "local",
"command": [
"uvx",
"mlflow_mcp_server"
],
"environment": {
"MLFLOW_TRACKING_URI": "http://localhost:5000"
}
}
}
}
