superset-mcp
An MCP server that provides AI assistants with full access to Apache Superset instances, enabling interaction with dashboards, charts, datasets, databases, and SQL execution capabilities.
README
superset-mcp
MCP (Model Context Protocol) server for Apache Superset. Gives AI assistants full access to your Superset instance — dashboards, charts, datasets, databases, and SQL execution.
Prerequisites
- uv — Python package manager
- Access to a running Apache Superset instance
Setup (takes ~1 minute)
1. Clone the repo
git clone <repo-url>
cd superset-mcp
2. Configure credentials
cp .env.example .env
Edit .env:
SUPERSET_URL=http://your-superset-host:8088
SUPERSET_USERNAME=your-username
SUPERSET_PASSWORD=your-password
3. Test it works
uv run superset-mcp
You should see the MCP server start without errors. Press Ctrl+C to stop.
Connect to your AI client
Replace /ABSOLUTE/PATH/TO/superset-mcp with the actual path where you cloned the repo.
Claude Code
Add to ~/.claude/settings.json (or project-level .claude/settings.json):
{
"mcpServers": {
"superset": {
"command": "uv",
"args": ["--directory", "/ABSOLUTE/PATH/TO/superset-mcp", "run", "superset-mcp"],
"env": {
"SUPERSET_URL": "http://your-superset-host:8088",
"SUPERSET_USERNAME": "your-username",
"SUPERSET_PASSWORD": "your-password"
}
}
}
}
Or run in terminal:
claude mcp add superset -- uv --directory /ABSOLUTE/PATH/TO/superset-mcp run superset-mcp
Claude Desktop
Add to ~/Library/Application Support/Claude/claude_desktop_config.json (macOS)
or %APPDATA%\Claude\claude_desktop_config.json (Windows):
{
"mcpServers": {
"superset": {
"command": "uv",
"args": ["--directory", "/ABSOLUTE/PATH/TO/superset-mcp", "run", "superset-mcp"],
"env": {
"SUPERSET_URL": "http://your-superset-host:8088",
"SUPERSET_USERNAME": "your-username",
"SUPERSET_PASSWORD": "your-password"
}
}
}
}
Cursor
Add to .cursor/mcp.json in your project or ~/.cursor/mcp.json globally:
{
"mcpServers": {
"superset": {
"command": "uv",
"args": ["--directory", "/ABSOLUTE/PATH/TO/superset-mcp", "run", "superset-mcp"],
"env": {
"SUPERSET_URL": "http://your-superset-host:8088",
"SUPERSET_USERNAME": "your-username",
"SUPERSET_PASSWORD": "your-password"
}
}
}
}
Available Tools
Dashboards
| Tool | Description |
|---|---|
list_dashboards |
List all dashboards (with optional search) |
get_dashboard |
Get a dashboard by ID or slug |
get_dashboard_charts |
Get all charts in a dashboard |
get_dashboard_datasets |
Get all datasets used by a dashboard |
create_dashboard |
Create a new dashboard |
update_dashboard |
Update title, layout, metadata |
publish_dashboard |
Publish a draft dashboard |
copy_dashboard |
Duplicate a dashboard |
delete_dashboard |
Delete a dashboard |
Charts
| Tool | Description |
|---|---|
list_charts |
List all charts (with optional search) |
get_chart |
Get a chart by ID or UUID |
get_chart_data |
Fetch the latest data for a chart |
create_chart |
Create a new chart |
update_chart |
Update chart properties |
delete_chart |
Delete a chart |
Datasets
| Tool | Description |
|---|---|
list_datasets |
List all datasets |
get_dataset |
Get a dataset by ID or UUID |
create_dataset |
Create from a table or SQL query |
get_or_create_dataset |
Get existing or create new |
refresh_dataset |
Sync columns from source table |
update_dataset |
Update dataset properties |
get_dataset_related_objects |
See which charts/dashboards use it |
delete_dataset |
Delete a dataset |
Databases
| Tool | Description |
|---|---|
list_databases |
List all database connections |
get_database |
Get a database connection by ID |
list_schemas |
List schemas in a database |
list_tables |
List tables in a schema |
get_table_metadata |
Get column info for a table |
get_select_star |
Get a SELECT * template for a table |
SQL
| Tool | Description |
|---|---|
execute_sql |
Run a SQL query and get results |
format_sql |
Pretty-print a SQL query |
estimate_query_cost |
Estimate query cost (if supported) |
list_saved_queries |
List saved SQL queries |
save_query |
Save a SQL query |
Example prompts
Once connected to your AI assistant:
- "List all published dashboards"
- "Create a new dashboard called 'Sales Overview'"
- "Show me all charts in dashboard 11"
- "Run a SQL query on database 2: SELECT count() FROM orders"*
- "What datasets are used by the 'Revenue' dashboard?"
- "Create a bar chart using dataset 5 showing sales by region"
推荐服务器
Baidu Map
百度地图核心API现已全面兼容MCP协议,是国内首家兼容MCP协议的地图服务商。
Playwright MCP Server
一个模型上下文协议服务器,它使大型语言模型能够通过结构化的可访问性快照与网页进行交互,而无需视觉模型或屏幕截图。
Magic Component Platform (MCP)
一个由人工智能驱动的工具,可以从自然语言描述生成现代化的用户界面组件,并与流行的集成开发环境(IDE)集成,从而简化用户界面开发流程。
Audiense Insights MCP Server
通过模型上下文协议启用与 Audiense Insights 账户的交互,从而促进营销洞察和受众数据的提取和分析,包括人口统计信息、行为和影响者互动。
VeyraX
一个单一的 MCP 工具,连接你所有喜爱的工具:Gmail、日历以及其他 40 多个工具。
graphlit-mcp-server
模型上下文协议 (MCP) 服务器实现了 MCP 客户端与 Graphlit 服务之间的集成。 除了网络爬取之外,还可以将任何内容(从 Slack 到 Gmail 再到播客订阅源)导入到 Graphlit 项目中,然后从 MCP 客户端检索相关内容。
Kagi MCP Server
一个 MCP 服务器,集成了 Kagi 搜索功能和 Claude AI,使 Claude 能够在回答需要最新信息的问题时执行实时网络搜索。
e2b-mcp-server
使用 MCP 通过 e2b 运行代码。
Neon MCP Server
用于与 Neon 管理 API 和数据库交互的 MCP 服务器
Exa MCP Server
模型上下文协议(MCP)服务器允许像 Claude 这样的 AI 助手使用 Exa AI 搜索 API 进行网络搜索。这种设置允许 AI 模型以安全和受控的方式获取实时的网络信息。