Skip to content
mcp/harbor
Grok

mlflow for Grok

io.github.us-all/mlflow

MLflow MCP — experiments, runs, registered models, versions, traces, assessments (MLflow 3)

client:Grok transport:stdio runtime:npm

Install mlflow in Grok

.mcp.json (in your project root)

Held in this page only — never stored, logged, or sent anywhere but back to your screen. 

{
  "mcpServers": {
    "mlflow": {
      "type": "stdio",
      "command": "npx",
      "args": [
        "-y",
        "@us-all/mlflow-mcp"
      ],
      "env": {
        "MLFLOW_TRACKING_URI": "<MLFLOW_TRACKING_URI>",
        "MLFLOW_TRACKING_TOKEN": "<MLFLOW_TRACKING_TOKEN>",
        "MLFLOW_TRACKING_USERNAME": "<MLFLOW_TRACKING_USERNAME>",
        "MLFLOW_TRACKING_PASSWORD": "<MLFLOW_TRACKING_PASSWORD>",
        "MLFLOW_EXPERIMENT_ID": "<MLFLOW_EXPERIMENT_ID>",
        "MLFLOW_TOOLS": "<MLFLOW_TOOLS>",
        "MLFLOW_DISABLE": "<MLFLOW_DISABLE>",
        "MLFLOW_ALLOW_WRITE": "<MLFLOW_ALLOW_WRITE>"
      }
    }
  }
}

Grok Build reads Claude Code's .mcp.json and Claude Desktop's config unchanged, so a server you have already set up there needs nothing new. The Grok web app and X integration do not take custom servers. Grok docs

mlflow in other clients

mlflow MCP server