mlflow

MCP ServerMCP Registry官方收录

io.github.us-all/mlflow · v1.12.4

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

源仓库 ↗

概览

mlflow 是一个MCP Server，收录自官方 MCP Registry。支持 stdio 传输。本页提供 Cursor、Claude Code 等客户端的安装配置片段。

安装

选择你的平台查看安装方式

{
  "mcpServers": {
    "mlflow": {
      "command": "npx",
      "args": [
        "-y",
        "@us-all/mlflow-mcp"
      ],
      "env": {
        "MLFLOW_TRACKING_URI": "<MLFLOW_TRACKING_URI>"
      }
    }
  }
}

环境变量

MLFLOW_TRACKING_URI必填

MLflow tracking server URI (e.g. http://localhost:5050, https://mlflow.example.com).

MLFLOW_TRACKING_TOKEN可选secret

Bearer token for authenticated MLflow servers (e.g. Databricks).

MLFLOW_TRACKING_USERNAME可选

Basic-auth username (alternative to token).

MLFLOW_TRACKING_PASSWORD可选secret

Basic-auth password (alternative to token).

MLFLOW_EXPERIMENT_ID可选

Default experiment ID for run-creation tools.

MLFLOW_TOOLS可选

Comma-separated category allowlist. Default: all categories enabled.

MLFLOW_DISABLE可选

Comma-separated category disablelist.

MLFLOW_ALLOW_WRITE可选

Set to 'true' to enable write/destructive tools. Default read-only.

统一 Manifest

{
  "id": "io.github.us-all/mlflow",
  "type": "mcp-server",
  "version": "1.12.4",
  "displayName": "mlflow",
  "description": "MLflow MCP — experiments, runs, registered models, versions, traces, assessments (MLflow 3)",
  "repository": {
    "url": "https://github.com/us-all/mlflow-mcp-server",
    "source": "github"
  },
  "distribution": {
    "packages": [
      {
        "registryType": "npm",
        "identifier": "@us-all/mlflow-mcp",
        "version": "1.12.4",
        "transport": "stdio",
        "environmentVariables": [
          {
            "name": "MLFLOW_TRACKING_URI",
            "description": "MLflow tracking server URI (e.g. http://localhost:5050, https://mlflow.example.com).",
            "isRequired": true
          },
          {
            "name": "MLFLOW_TRACKING_TOKEN",
            "description": "Bearer token for authenticated MLflow servers (e.g. Databricks).",
            "isSecret": true
          },
          {
            "name": "MLFLOW_TRACKING_USERNAME",
            "description": "Basic-auth username (alternative to token)."
          },
          {
            "name": "MLFLOW_TRACKING_PASSWORD",
            "description": "Basic-auth password (alternative to token).",
            "isSecret": true
          },
          {
            "name": "MLFLOW_EXPERIMENT_ID",
            "description": "Default experiment ID for run-creation tools."
          },
          {
            "name": "MLFLOW_TOOLS",
            "description": "Comma-separated category allowlist. Default: all categories enabled."
          },
          {
            "name": "MLFLOW_DISABLE",
            "description": "Comma-separated category disablelist."
          },
          {
            "name": "MLFLOW_ALLOW_WRITE",
            "description": "Set to 'true' to enable write/destructive tools. Default read-only."
          }
        ]
      }
    ],
    "remotes": []
  },
  "dependencies": [],
  "installTargets": [
    "claude-code",
    "claude-desktop",
    "cursor",
    "vscode"
  ],
  "keywords": [],
  "provenance": {
    "origin": "official-mcp-registry",
    "originalId": "io.github.us-all/mlflow",
    "originalUrl": "https://registry.modelcontextprotocol.io/v0.1/servers/io.github.us-all%2Fmlflow/versions/latest",
    "isOfficial": true,
    "status": "active"
  }
}

mlflow

概览

安装

环境变量

相关资源

RFP.ai

xenarch-mcp

api

agent-lsp

hostinger-api-mcp

Unterm

统一 Manifest