Superset MCP Integration

Name: Superset MCP Integration
Author: aptro

@aptro

リポジトリ

Superset MCP Integration について

connect to 50+ data stores via superset mcp server. Can use with open ai agent sdk, Claude app, cursor, windsurf

#mcp-superset #data-visualization #ai-integration

基本情報

カテゴリ

AI とエージェント

ライセンス

MIT

ランタイム

python

トランスポート

stdio

公開者

aptro

設定

以下の設定を使って、このサーバーを MCP 対応クライアントに追加してください。

{
  "darkMode": "light",
  "scale": 0,
  "locale": "en-US",
  "mcpServers": {
    "superset-mcp": {
      "command": "cmd",
      "args": [
        "/c",
        "npx",
        "-y",
        "@smithery/cli@latest",
        "run",
        "@aptro/superset-mcp",
        "--key",
        "83cb7c57-dd21-4b5c-a442-dd4b91d2cce4",
        "--config",
        "\"{\\\"supersetBaseUrl\\\":\\\"https://superset.supover.com/\\\"}\""
      ],
      "env": {
        "SUPERSET_USERNAME": "admin",
        "SUPERSET_PASSWORD": "thien123"
      }
    }
  }
}

ツール

ツールは検出されませんでした

ツールは README から自動的に抽出されます。メンテナーは ## Tools という見出しの下に記載することで、このタブに反映できます。

概要

What is Superset MCP Integration?

MCP server for interacting with Apache Superset, enabling AI agents to connect to and control a Superset instance programmatically.

How to use Superset MCP Integration?

Install via Smithery (npx -y @smithery/cli install @aptro/superset-mcp --client claude) or manually: set up Superset (tested with version 4.1.1) using Docker, clone the repo, create a .env file with SUPERSET_BASE_URL, SUPERSET_USERNAME, and SUPERSET_PASSWORD, install dependencies with uv pip install ., then run mcp install main.py for Claude Desktop.

Key features of Superset MCP Integration

Dashboard CRUD operations (list, get, create, update, delete)
Chart creation, update, and deletion
Database connection management and SQL validation
Dataset listing, retrieval, and creation
SQL Lab query execution and formatting
Tag management for organizing content

Use cases of Superset MCP Integration

Manage dashboards and charts via natural language requests to Claude
Execute, format, and estimate cost of SQL queries through Claude
Create and update database connections programmatically
List and inspect datasets, tables, schemas, and catalogs
Organize content by tagging dashboards, charts, and other objects

FAQ from Superset MCP Integration

How do I install the Superset MCP Integration?

Install automatically via Smithery or manually: start Superset (version 4.1.1) with Docker, configure .env with your Superset credentials, install dependencies with uv pip install ., then run mcp install main.py for Claude Desktop.

What MCP tools are available?

Over 60 tools covering authentication, dashboards, charts, databases, datasets, SQL Lab, queries, saved queries, user info, activity, system, tags, exploration, and advanced data types.

How are credentials stored and handled?

Superset credentials are stored only in your local .env file, and the access token is stored in .superset_token in the project directory. No credentials are transmitted to Claude or any third parties.

What version of Superset is supported?

The integration is tested with Superset version 4.1.1.

How can I troubleshoot authentication issues?

Verify your credentials in the .env file, ensure Superset is running and accessible at the URL specified, and check that the port used by the MCP server is not being used by another application.

「AI とエージェント」の他のコンテンツ

欢迎来到智言平台

Shy2593666979

AgentChat 是一个基于 LLM 的智能体交流平台，内置默认 Agent 并支持用户自定义 Agent。通过多轮对话和任务协作，Agent 可以理解并协助完成复杂任务。项目集成 LangChain、Function Call、MCP 协议、RAG、Memory、HITL、Skill、Milvus 和 ElasticSearch 等技术，实现高效的知识检索与工具调用，使用 FastAPI 构建高性能后端服务。

797

Solon Ai

opensolon

Java AI application development framework (supports LLM-tool,skill; RAG; MCP; Agent-ReAct,Team-Agent). Compatible with java8 ~ java25. It can also be embedded in SpringBoot, jFinal, Vert.x, Quarkus, and other frameworks.

416

1Panel

1Panel-dev

🔥 1Panel is a modern, open-source VPS control panel — and the only one with native AI agent support. Run Ollama models, deploy OpenClaw agents, and manage your entire server stack from one clean web interface.

36.1K