| name | metabase-mcp-connector |
| description | MCP connector for Metabase – enables AI-powered question building, dashboard creation, and data exploration through Claude |
| license | AGPL |
| tags | ["data","analytics","mcp","metabase","bi"] |
| difficulty | intermediate |
| time_to_master | 4-8 weeks |
| version | 1.0.0 |
Metabase MCP Connector
Overview
This skill enables Claude to interact with Metabase through the Model Context Protocol (MCP). It provides a bridge between Claude's AI capabilities and Metabase's REST API, allowing natural language control of Metabase operations, intelligent automation, and AI-powered assistance for Metabase workflows.
When to Use This Skill
- Question/query creation via natural language
- Dashboard generation and layout management
- Collection organization and permissions
- Alert and subscription configuration
- Database and table metadata management
Architecture
┌─────────────┐ ┌─────────────────┐ ┌──────────────────┐
│ Claude │────▶│ MCP Server │────▶│ Metabase │
│ (Client) │◀────│ (TypeScript) │◀────│ (REST API )│
└─────────────┘ └─────────────────┘ └──────────────────┘
Core Concepts
MCP Server Setup
The connector implements an MCP server that exposes Metabase operations as tools Claude can invoke. The server translates natural language intentions into REST API calls.
Key Endpoints/Interfaces
/api/card, /api/dashboard, /api/collection, /api/database, /api/alert
Implementation
import { McpServer } from "@modelcontextprotocol/sdk/server/mcp.js";
import { StdioServerTransport } from "@modelcontextprotocol/sdk/server/stdio.js";
import { z } from "zod";
const server = new McpServer({
name: "metabase-mcp-connector",
version: "1.0.0",
});
server.tool(
"list_resources",
"List and query Metabase resources with optional filters",
{
query: z.string().optional().describe("Search query or filter"),
limit: z.number().optional().describe("Max results to return"),
},
async ({ query, limit }) => {
const response = await fetch(`${BASE_URL}/api/card`, {
headers: { "Authorization": `Bearer ${API_KEY}` },
});
const data = await response.json();
return {
: [{ : , : .(data, , ) }],
};
}
);
server.(
,
,
{
: z.().(),
: z.({}).().().(),
},
({ name, config }) => {
response = (, {
: ,
: {
: ,
: ,
},
: .({ name, ...config }),
});
data = response.();
{
: [{ : , : }],
};
}
);
server.(
,
,
{
: z.().(),
: z.().().(),
},
({ , timeframe }) => {
response = (, {
: { : },
});
data = response.();
{
: [{ : , : .(data, , ) }],
};
}
);
transport = ();
server.(transport);
Claude Desktop Configuration
{
"mcpServers": {
"metabase-mcp-connector": {
"command": "node",
"args": ["path/to/metabase-mcp-connector/index.js"],
"env": {
"METABASE_API_KEY": "your-api-key",
"METABASE_BASE_URL": "https://your-instance-url"
}
}
}
}
Best Practices
- Authentication: Store API keys securely using environment variables; never hardcode credentials
- Rate Limiting: Implement request throttling to respect Metabase API rate limits
- Error Handling: Provide clear, actionable error messages for common failure scenarios
- Pagination: Handle paginated responses for large datasets efficiently
- Caching: Cache frequently accessed read-only data to reduce API calls
- Security: Validate all inputs before passing to the Metabase API; sanitize outputs
- Logging: Log all API interactions for debugging and audit purposes
Example Prompts
"Create a sales dashboard with revenue by region, top products, and month-over-month growth charts"
Security Considerations
- All API credentials must be stored as environment variables
- Implement input validation and sanitization for all tool parameters
- Use HTTPS for all API communications
- Follow the principle of least privilege for API token permissions
- Audit log all write operations for compliance tracking
Resources
Changelog
| Version | Date | Changes |
|---|
| 1.0.0 | 2026-04-01 | Initial MCP connector skill |
Part of SkillGalaxy - 10,000+ comprehensive skills for AI-assisted development.
