Metabase MCP Server
A that gives AI assistants full access to your analytics platform — dashboards, cards, databases, tables, collections, and more.
接入你的智能体
發布者自己的指令。不是 PlugMCP 端點。
用我們的金鑰與日誌託管一份副本。
npx -y @easecloudio/[email protected]Claude Code 沒有本機指令的安裝連結。複製下方指令並在終端機中執行。
claude mcp add easecloudio-mcp-metabase-server -- npx -y @easecloudio/mcp-metabase-server@1.3.0在終端機中執行。
{ "mcpServers": { "easecloudio-mcp-metabase-server": { "command": "npx", "args": [ "-y", "@easecloudio/[email protected]" ] } }}claude_desktop_config.json
遠端 URL 還是本機指令? 兩種安裝方式的差異
來自發布者
A that gives AI assistants full access to your analytics platform — dashboards, cards, databases, tables, collections, and more.
MCP server for Metabase — 96 tools covering dashboards, cards, databases, tables, collections, public sharing, schema cache, and SQL-to-MBQL conversion
Developed and maintained by EaseCloud — cloud-native, AI-driven, and data infrastructure solutions.
export METABASE_URL=https://your-metabase-instance.com
export METABASE_API_KEY=your_metabase_api_key
npx @easecloudio/mcp-metabase-server
npx @easecloudio/mcp-metabase-server
npm install -g @easecloudio/mcp-metabase-server
mcp-metabase-server
docker build -t mcp-metabase-server .
docker run -it --rm \
-e METABASE_URL=https://your-metabase-instance.com \
-e METABASE_API_KEY=your_metabase_api_key \
mcp-metabase-server
API Key (preferred):
METABASE_URL=https://your-metabase-instance.com
METABASE_API_KEY=your_metabase_api_key
Username / Password (fallback):
METABASE_URL=https://your-metabase-instance.com
METABASE_USERNAME=your_username
METABASE_PASSWORD=your_password
Copy .env.example to .env and fill in your values.
Set TOOL_MODE to control which tools are exposed to the AI. Useful for limiting surface area or preventing accidental writes.
TOOL_MODE=essential # smallest surface area
TOOL_MODE=read # read-only
TOOL_MODE=all # everything (default)
MacOS: ~/Library/Application Support/Claude/claude_desktop_config.json
Windows: %APPDATA%/Claude/claude_desktop_config.json
Using npx:
{
"mcpServers": {
"metabase": {
"command": "npx",
"args": ["@easecloudio/mcp-metabase-server"],
"env": {
"METABASE_URL": "https://your-metabase-instance.com",
"METABASE_API_KEY": "your_metabase_api_key"
}
}
}
}
With tool filtering:
{
"mcpServers": {
"metabase": {
"command": "npx",
"args": ["@easecloudio/mcp-metabase-server"],
"env": {
"METABASE_URL": "https://your-metabase-instance.com",
"METABASE_API_KEY": "your_metabase_api_key",
"TOOL_MODE": "essential"
}
}
}
}
Using a local build:
{
"mcpServers": {
"metabase": {
"command": "node",
"args": ["/path/to/metabase-server/dist/index.js"],
"env": {
"METABASE_URL": "https://your-metabase-instance.com",
"METABASE_API_KEY": "your_metabase_api_key"
}
}
}
}
Username / password fallback:
{
"mcpServers": {
"metabase": {
"command": "npx",
"args": ["@easecloudio/mcp-metabase-server"],
"env": {
"METABASE_URL": "https://your-metabase-instance.com",
"METABASE_USERNAME": "your_username",
"METABASE_PASSWORD": "your_password"
}
}
}
}
These tools enable an AI to convert native SQL questions into interactive MBQL questions. Metabase has no REST API for this conversion — it requires field IDs, which these tools cache locally.
How it works:
get_card — extract the SQL and database_idget_schema_cache — get tables + field IDs for MBQL references like ["field", 42, null]create_card — save the new interactive questionCache is stored at ~/.easecloud/metabase-mcp/cache/{url-hash}/ with a 24-hour TTL and scoped per Metabase instance.
Access Metabase entities directly via metabase:// URIs:
npm install
npm run build # compile TypeScript → dist/
npm run watch # incremental rebuild
npm run dev # build + start
npm run inspector # launch MCP Inspector for debugging
MCP servers communicate over stdio, which makes direct debugging awkward. Use the MCP Inspector:
npm run inspector
The Inspector provides a browser UI for sending tool calls and inspecting responses.
EaseCloud is a cloud consulting and solutions company specializing in:
We built this project to contribute to the open-source MCP ecosystem while demonstrating our expertise in integration, automation, and cloud solutions.
If your team is adopting Metabase at scale or looking to integrate AI with your BI stack, get in touch — we provide consulting, customization, and managed support for enterprises.
Found a bug or have a feature request?
Please include:
Contributions are welcome. Visit the GitHub repository to submit issues or pull requests.
MIT — see LICENSE for details.
MCP server for Metabase — 96 tools covering dashboards, cards, databases, tables, collections, public sharing, schema cache, and SQL-to-MBQL conversion
{ "mcpServers": { "easecloudio-mcp-metabase-server": { "command": "npx", "args": [ "-y", "@easecloudio/[email protected]" ] } }}工具
尚無工具清單。遠端伺服器會在首次健康檢查後取得工具清單。
常見問題
在本頁複製適用於 Cursor、Claude Desktop、Claude Code 或 VS Code 的 stdio 設定。它使用發布者的安裝方式,而不是 PlugMCP 代理伺服器。
這筆記錄未列出必要的環境變數。
@easecloudio/mcp Metabase Server 透過 stdio 在本機執行。
上次檢查時間:2026-11-16。 MCP server for Metabase — 96 tools covering dashboards, cards, databases, tables, collections, public sharing, schema cache, and SQL-to-MBQL conversion