// SCAN REPORT

Metabase MCP Server

12 tools. 8 can modify or destroy data without limits.

2 destructive tools with no built-in limits. Policy required.

Last updated: 4 Jul 2026

8 can modify or destroy data

4 read-only

12 tools total

Community server · catalogue entry verified 04/07/2026

How to control Metabase MCP Server ↓

TOOL MAP

What Metabase MCP Server exposes to your agents

Read (4) Write / Execute (6) Destructive / Financial (2)

Running more than one server? Check your whole stack →

MOST DANGEROUS TOOLS

Critical Risk

The most dangerous Metabase MCP Server tools

Destructive · High delete_card This tool permanently removes a Metabase card (saved question), which cannot be undone. Destructive · High delete_dashboard This tool permanently removes a dashboard and its associated configuration from Metabase. Execute · High execute_card While 'execute_card' primarily reads and returns query results (lower risk), it runs pre-defined Metabase cards which may contain complex queries with side effects, aggregations, or external data source calls. Execute · High execute_query Although execute_query could theoretically be constrained to SELECT-only queries, the description provides no such assurance.

8 of Metabase MCP Server's 12 tools can modify, destroy, or commit something on every call — and an agent calls them with no built-in limits.

POLICY

How to control Metabase MCP Server

PolicyLayer is an MCP gateway — it sits between your AI agents and Metabase MCP Server, and nothing reaches the server without passing your rules. These are the rules we recommend:

Deny destructive operations

{
  "delete_card": {
    "deny_if": [
      {
        "conditions": [],
        "on_deny": "Blocked by default. Requires approval."
      }
    ]
  }
}

Destructive tools should never be available to autonomous agents without human approval.

Rate limit write operations

{
  "create_card": {
    "limits": [
      {
        "counter": "create_card_per_hour",
        "window": "hour",
        "max": 30,
        "scope": "grant"
      }
    ]
  }
}

Prevents bulk unintended modifications from agents caught in loops.

Cap read operations

{
  "get_dashboard_details": {
    "limits": [
      {
        "counter": "get_dashboard_details_per_minute",
        "window": "minute",
        "max": 60,
        "scope": "grant"
      }
    ]
  }
}

Controls API costs and prevents retry loops from exhausting upstream rate limits.

Create a free account and register Metabase MCP Server — nothing to install.
Add these rules — paste them, or build them visually. Tune the limits to your setup.
Point your MCP client (Claude, Cursor, anything) at your gateway URL.

ENFORCE POLICY ON METABASE →

Instant setup, no code required.

FULL CATALOGUE

All 12 Metabase MCP Server tools

DESTRUCTIVE 2 tools

Destructive delete_card Delete a Metabase question (card). Destructive delete_dashboard Delete a Metabase dashboard.

EXECUTE 2 tools

Execute execute_card Execute a Metabase question/card and get results Execute execute_query Execute a SQL query against a specified database.

WRITE 4 tools

Write create_card Create a new Metabase question (card). Write create_dashboard Create a new Metabase dashboard. Write update_card Update an existing Metabase question (card). Write update_dashboard Update an existing Metabase dashboard.

READ 4 tools

Read get_dashboard_details Get full details for a specific dashboard, including its dashcards and parameters. Read list_cards List Metabase cards (questions/models). Can be filtered. Read list_dashboards List Metabase dashboards. Can be filtered. Read list_databases List Metabase databases. Can be filtered.

EXPLORE

Related servers

Other MCP servers with similar tools — same risk classification, starter policies for each.

FAQ

Questions about Metabase MCP Server

Can an AI agent delete data through the Metabase MCP Server MCP server? +

Yes. The Metabase MCP Server server exposes 2 destructive tools including delete_card, delete_dashboard. These permanently remove resources with no undo. PolicyLayer blocks destructive tools by default so they never reach the upstream server.

How do I prevent bulk modifications through Metabase MCP Server? +

The Metabase MCP Server server has 4 write tools including create_card, create_dashboard, update_card. Set a rate limit in your policy -- for example, 10 calls per hour prevents an agent from making more than 10 modifications per hour. PolicyLayer enforces this at the gateway, before calls reach Metabase MCP Server.

How many tools does the Metabase MCP Server MCP server expose? +

12 tools across 4 categories: Destructive, Execute, Read, Write. 4 are read-only. 8 can modify, create, or delete data.

How do I enforce a policy on Metabase MCP Server? +

Register the Metabase MCP Server MCP server in PolicyLayer, apply the suggested rules above (adjust the limits to your use case), and point your AI client at the PolicyLayer proxy URL instead of the server directly. Your agents keep the same tools; PolicyLayer evaluates every call against policy before it executes. Nothing to install, live in minutes.

Enforce policy on every Metabase MCP Server tool call.

Deterministic rules across all 12 Metabase MCP Server tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.

ENFORCE POLICY ON METABASE →

Instant setup, no code required.

12 Metabase MCP Server tools catalogued and risk-classified — across an index of 43,000+ MCP servers.