Mlflow runs on your own machine — the client starts it, so there is no endpoint to ping. 91 installs a week from npm. Last commit 10 Jul 2026.
MLflow MCP — experiments, runs, registered models, versions, traces, assessments (MLflow 3)
We read the source, 18 h ago · rules 3dff92dd89df
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.
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.
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 -- npx -y @us-all/mlflow-mcp
{
"mcpServers": {
"mlflow": {
"args": [
"-y",
"@us-all/mlflow-mcp"
],
"command": "npx"
}
}
}
[mcp_servers.mlflow]
command = "npx"
args = ["-y", "@us-all/mlflow-mcp"]
{
"mcpServers": {
"mlflow": {
"args": [
"-y",
"@us-all/mlflow-mcp"
],
"command": "npx"
}
}
}
{
"mcpServers": {
"mlflow": {
"args": [
"-y",
"@us-all/mlflow-mcp"
],
"command": "npx"
}
}
}
This one needs environment variables set before it will start:
MLFLOW_TRACKING_URI (MLflow tracking server URI (e.g. http://localhost:5050, https://mlflow.example.com).), 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.).
The author declared them in the registry entry; get the values from the project itself.
Inspect and manage Verlon AI gates, logs, recommendations, and experiments from any MCP client.
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.
Structured observability for AI agents. Trace steps, decisions, and errors. MCP server + CLI viewer.
Track how 350+ AI models mention your brand — manage projects, run scans, analyze results
Search and trace US federal rules across the Federal Register, eCFR, and Regulations.gov.
MCP server for Sentry — error tracking, issues, releases, events, and projects for AI assistants.
Traces which neurons and attention heads drive a language model's output via MCP tools.
Answers built from our own checks of this server.