MetabaseSAFE
A Model Context Protocol server that integrates AI assistants with Metabase analytics platform
Overview
From the repository's own README, as read at the audited commit. Badges and raw HTML are left out.
Author: Hyeongjun Yu (@hyeongjun-dev)
[](https://smithery.ai/server/@hyeongjun-dev/metabase-mcp-server)
A Model Context Protocol server that integrates AI assistants with Metabase analytics platform.
Overview
This TypeScript-based MCP server provides seamless integration with the Metabase API, enabling AI assistants to directly interact with your analytics data. Designed for Claude and other MCP-compatible AI assistants, this server acts as a bridge between your analytics platform and conversational AI.
Key Features
- Resource Access: Navigate Metabase resources via intuitive
metabase://URIs - Two Authentication Methods: Support for both session-based and API key authentication
- Structured Data Access: JSON-formatted responses for easy consumption by AI assistants
- Comprehensive Logging: Detailed logging for easy debugging and monitoring
- Error Handling: Robust error handling with clear error messages
Available Tools
The server exposes the following tools for AI assistants:
list_dashboards: Retrieve all available dashboards in your Metabase instancelist_cards: Get all saved questions/cards in Metabaselist_databases: View all connected database sourcesexecute_card: Run saved questions and retrieve results with optional parametersget_dashboard_cards: Extract all cards from a specific dashboardexecute_query: Execute custom SQL queries against any connected database
Configuration
The server supports two authentication methods:
Option 1: Username and Password Authentication
# Required METABASE_URL=https://your-metabase-instance.com [email protected] METABASE_PASSWORD=your_password # Optional LOG_LEVEL=info # Options: debug, info, warn, error, fatal
Option 2: API Key Authentication (Recommended for Producti
909ed38ccfbbOBSERVED · 2026-10-08Connect
Built from this server's own package name, version and transport as found in its source — not copied from anyone's documentation, so it cannot drift against a page we do not control. Replace the environment placeholders with a token scoped to the least it needs.
claude mcp add metabase-mcp-server --env METABASE_API_KEY=${METABASE_API_KEY} --env METABASE_PASSWORD=${METABASE_PASSWORD} -- npx -y [email protected]{
"mcpServers": {
"metabase-mcp-server": {
"command": "npx",
"args": [
"-y",
"[email protected]"
],
"env": {
"METABASE_API_KEY": "${METABASE_API_KEY}",
"METABASE_PASSWORD": "${METABASE_PASSWORD}"
}
}
}
}Exposed tools (6)
4 read · 2 write · 0 destructive.
| Tool | Risk | Description |
|---|---|---|
execute_card | write | Execute a Metabase question/card and get results |
execute_query | write | Execute a SQL query against a Metabase database |
get_dashboard_cards | read | Get all cards in a dashboard |
list_cards | read | List all questions/cards in Metabase |
list_dashboards | read | List all dashboards in Metabase |
list_databases | read | List all databases in Metabase |
Trust audit
SAFEgrade B · trust 89/100 Nothing in the source contradicts what it says it does. Grade A is reserved for packages that have also passed the behavioural sandbox.
| Layer | What it checks | Result |
|---|---|---|
| L0 | Provenance & inventory | PASS |
| L1 | Static analysis of the code | PASS |
| L2 | Instruction surface (what it tells the agent) | PASS |
| L3 | Class-specific surface | PASS |
| L4 | Behavioural (sandbox) | SKIPPED |
What the source does
- Filesystem
- none-observed
- Network
- declared (1 observation(s))
- Shell
- none-observed
- Dependencies
- not all pinned
- Secrets in source
- none-found
Findings (2)
@modelcontextprotocol/sdk, dotenv, zod, @types/node, typescript, eslint, @typescript-eslint/eslint-plugin, @typescript-eslint/parser
Gates applied: no_behavioural_pass, no_license.
909ed38ccfbbfull audit observations/trust-audit/mcp-server/hyeongjun-dev__metabase-2.json · Report an issue / request a re-scanAudit history
Every audit this server has had. A grade with a past is a grade somebody is still checking.
| Date | Source | Verdict | Grade | Score | Change |
|---|---|---|---|---|---|
| 2026-10-08 | 909ed38ccfbb | SAFE | B | 89 | first audit |
Questions
What is the Metabase MCP server?
A Model Context Protocol server that integrates AI assistants with Metabase analytics platform
What tools does Metabase expose?
6 in total: 4 read-only, 2 that write, and 0 that can delete or overwrite. Every one is listed on this page with its risk.
Is Metabase safe to connect to an agent?
The audit found nothing in the source that contradicts what it says it does, and graded it B (89/100). Grade A is held back for packages that have also passed a sandboxed behavioural run, which is why a clean server reads B.
What credentials does Metabase need?
It reads METABASE_API_KEY and METABASE_PASSWORD from the environment. Give it a token scoped to the least it needs — an agent that can be talked into calling a tool can be talked into calling it with your credentials.
How does Metabase run?
It speaks stdio, so it runs as a local process your client starts. It is published on npm as metabase-mcp-server at 0.1.0.
How current is this page?
The grade is for one exact copy of the source (909ed38ccfbb), read on 2026-10-08. The repository is watched and re-audited when it changes.