Mlflow runs on your own machine — the client starts it, so there is no endpoint to ping. 109 installs a week from npm. Last commit 10 Jul 2026.
MLflow MCP — experiments, runs, registered models, versions, traces, assessments (MLflow 3)
What the code does
We read the source, 2 d ago · rules 995398eba69f
What this server is able to do. For an MCP server this is often the job itself — a terminal server runs commands because that is what it is for. Listed so you know what you are plugging in, not as an accusation.
function update(){ document.getElementById('app').innerHTML = render(window.openai && window.openai.toolOutput); }
Is this your server and something here is wrong? Tell us — corrections are free and do not require a plan.
This code can reach further than it looks
We found places where it runs commands, builds paths or queries from values it is given. None of that is a flaw by itself — it becomes one when the code changes, and code changes quietly between releases. We re-read it on every one.
Connect this server
This server runs on your own machine — install it with the package manager and the client starts it for you. Package name taken from the official registry entry.
claude mcp add mlflow -e 'MLFLOW_TRACKING_URI=<MLFLOW_TRACKING_URI>' -- npx -y @us-all/mlflow-mcp{
"mcpServers": {
"mlflow": {
"command": "npx",
"args": [
"-y",
"@us-all/mlflow-mcp"
],
"env": {
"MLFLOW_TRACKING_URI": "<MLFLOW_TRACKING_URI>"
}
}
}
}[mcp_servers.mlflow]
command = "npx"
args = ["-y", "@us-all/mlflow-mcp"]
env = { MLFLOW_TRACKING_URI = "<MLFLOW_TRACKING_URI>" }{
"mcpServers": {
"mlflow": {
"command": "npx",
"args": [
"-y",
"@us-all/mlflow-mcp"
],
"env": {
"MLFLOW_TRACKING_URI": "<MLFLOW_TRACKING_URI>"
}
}
}
}{
"servers": {
"mlflow": {
"type": "stdio",
"command": "npx",
"args": [
"-y",
"@us-all/mlflow-mcp"
],
"env": {
"MLFLOW_TRACKING_URI": "<MLFLOW_TRACKING_URI>"
}
}
}
}Put your own value in place of
<MLFLOW_TRACKING_URI> (MLflow tracking server URI (e.g. http://localhost:5050, https://mlflow.example.com)).
The author’s registry entry marks it as required.
Optional settings from the registry entry, left out of the block above:
MLFLOW_TRACKING_TOKEN (Bearer token for authenticated MLflow servers (e.g. Databricks)), MLFLOW_TRACKING_USERNAME (Basic-auth username (alternative to token)), MLFLOW_TRACKING_PASSWORD (Basic-auth password (alternative to token)), MLFLOW_EXPERIMENT_ID (Default experiment ID for run-creation tools), MLFLOW_TOOLS (Comma-separated category allowlist. Default: all categories enabled), MLFLOW_DISABLE (Comma-separated category disablelist), MLFLOW_ALLOW_WRITE (Set to 'true' to enable write/destructive tools. Default read-only).
Alternatives to Mlflow
same job, measured the same wayRead and score Opik traces, experiments, datasets and prompts from your AI assistant.
Inspect and manage Verlon AI gates, logs, recommendations, and experiments from any MCP client.
Run 3D CAD operations, pipelines, parametric models and STEP conversions on CAD Cloud with a key
Govern model, agent, skill, and MCP workflows with policy, approvals, traces, and usage analytics.
Inspect AgentMark traces and drive AgentMark Cloud: apps, experiments, metrics, deployments.
Search a registry of agent skills and MCP servers, then run them for real. No install, traced.
Query OpenTelemetry traces from agent runs through MCP.
Structured observability for AI agents. Trace steps, decisions, and errors. MCP server + CLI viewer.
Mlflow — questions
Answers built from our own checks of this server.