Config is the same across clients — only the file and path differ.
{
"mcpServers": {
"metabase": {
"env": {
"METABASE_URL": "https://your-metabase-instance.com",
"METABASE_API_KEY": "your_metabase_api_key"
},
"args": [
"@cognitionai/metabase-mcp-server"
],
"command": "npx"
}
}
}Are you the author?
Add this badge to your README to show your security score and help users find safe servers.
A comprehensive Model Context Protocol (MCP) server for Metabase integration, providing AI assistants with full access to Metabase's analytics platform.
Run this in your terminal to verify the server starts. Then let us know if it worked — your result helps other developers.
npx -y 'export' 2>&1 | head -1 && echo "✓ Server started successfully"
After testing, let us know if it worked:
Five weighted categories — click any category to see the underlying evidence.
No known CVEs.
Checked export against OSV.dev.
Click any tool to inspect its schema.
Be the first to review
Have you used this server?
Share your experience — it helps other developers decide.
Sign in to write a review.
Others in analytics
MCP Server for GCP environment for interacting with various Observability APIs.
⚡ A Simple / Speedy / Secure Link Shortener with Analytics, 100% run on Cloudflare.
35+ AI tools for TCG card grading, Monte Carlo pricing, 370K+ product search. BYOK.
MCP server for InsightSentry financial data API - market data, options, screeners, and more
MCP Security Weekly
Get CVE alerts and security updates for Metabase Mcp Server and similar servers.
Start a conversation
Ask a question, share a tip, or report an issue.
Sign in to join the discussion.
A comprehensive Model Context Protocol (MCP) server for Metabase integration, providing AI assistants with full access to Metabase's analytics platform.
# Install and run with npx
export METABASE_URL=https://your-metabase-instance.com
export METABASE_API_KEY=your_metabase_api_key
npx @cognitionai/metabase-mcp-server
💡 Recommended: Node.js 20.19.0+ and npm 8.0.0+ for optimal compatibility
npx @cognitionai/metabase-mcp-server
npm install -g @cognitionai/metabase-mcp-server
metabase-mcp-server
docker run -it --rm \
-e METABASE_URL=https://your-metabase-instance.com \
-e METABASE_API_KEY=your_metabase_api_key \
ghcr.io/CognitionAI/metabase-mcp-server
API Key Authentication (Preferred):
export METABASE_URL=https://your-metabase-instance.com
export METABASE_API_KEY=your_metabase_api_key
Username/Password Authentication (Fallback):
export METABASE_URL=https://your-metabase-instance.com
export METABASE_USERNAME=your_username
export METABASE_PASSWORD=your_password
The server supports command-line arguments to customize tool loading:
--essential (default): Load only essential tools--all: Load all 80+ available tools--write: Load only write/modification tools--read: Load only read-only tools# Using published package (recommended)
# Default behavior (essential tools only)
npx @cognitionai/metabase-mcp-server
# Load all tools
npx @cognitionai/metabase-mcp-server --all
# Load only write tools
npx @cognitionai/metabase-mcp-server --write
# Load only read-only tools
npx @cognitionai/metabase-mcp-server --read
# Using local development build
npm run build
node dist/server.js # Default (essential tools)
node dist/server.js --all # All tools
node dist/server.js --write # Write tools only
node dist/server.js --read # Read-only tools only
Add to your Claude Desktop config (~/Library/Application Support/Claude/claude_desktop_config.json on macOS):
Using published package:
{
"mcpServers": {
"metabase": {
"command": "npx",
"args": ["@cognitionai/metabase-mcp-server"],
"env": {
"METABASE_URL": "https://your-metabase-instance.com",
"METABASE_API_KEY": "your_metabase_api_key"
}
}
}
}
Using local development build:
{
"mcpServers": {
"metabase": {
"command": "node",
"args": ["/path/to/metabase-mcp-server/dist/server.js"],
"env": {
"METABASE_URL": "https://your-metabase-instance.com",
... [View full README on GitHub](https://github.com/CognitionAI/metabase-mcp-server#readme)