execute_query
Execute a SQL query against a Metabase database
This record as markdown: /tools/zsh52013148087-metabase-mcp/execute-query.md
What execute_query does on Metabase Analytics Integration Server
AI agents invoke execute_query to trigger actions in Metabase Analytics Integration Server. What it does depends on the arguments the agent supplies, and its effects often reach beyond the immediate call: builds kicked off, notifications sent, workflows started.
| Parameter | Type | Required | Description |
|---|---|---|---|
query | string | — | SQL query to execute |
database_id | number | — | ID of the database to query |
native_parameters | array | — | Optional parameters for the query |
Parameters from the server's own tool schema.
Why execute_query is rated High
SQL query execution is fundamentally an Execute-category risk because the effects are entirely argument-dependent: queries could SELECT (Read), INSERT/UPDATE (Write), DROP/DELETE (Destructive), or trigger other side effects based on the SQL provided. An AI agent given this tool without strict input validation could be manipulated into running destructive queries.
From the tool's definition Tool explicitly described as 'Execute a SQL query against a Metabase database'. The verb 'Execute' combined with 'SQL query' indicates arbitrary code execution capability.
Risk signalsAccepts freeform code/query input (query)
Attacks that exploit this kind of access
The rule that runs execute_query safely
PolicyLayer is an MCP gateway: it sits between your AI agents and Metabase Analytics Integration Server, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For execute_query, this is the rule to start with:
execute_query stays usable, but rate-capped: a runaway agent can't fire it dozens of times a minute. Everything else on the server is denied unless you say otherwise.
The button opens the PolicyLayer dashboard: create your workspace, connect Metabase Analytics Integration Server, apply this rule, and every execute_query call is checked against it from then on.
Questions about execute_query
Execute a SQL query against a Metabase database. It is categorised as a Execute tool in the Metabase Analytics Integration Server MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
execute_query accepts 3 parameters: query, database_id, native_parameters. The full parameter table on this page comes from the server's own tool schema.
Register the Metabase Analytics Integration Server MCP server in PolicyLayer and add a rule for execute_query: allow, deny, rate-limit, or require approval. Point your MCP client at the PolicyLayer proxy URL and the rule is enforced on every call, before it reaches Metabase Analytics Integration Server. Nothing to install.
execute_query is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.
Yes. Add a rate_limit block to the execute_query rule in your PolicyLayer policy. For example, setting max: 10 and window: 60 limits the tool to 10 calls per minute. Rate limits are tracked per agent session and reset automatically.
Set action: deny in the PolicyLayer policy for execute_query. The AI agent will receive a policy violation error and cannot call the tool. You can also include a reason field to explain why the tool is blocked.
execute_query is provided by the Metabase Analytics Integration Server MCP server (zsh52013148087/metabase-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
More on Metabase Analytics Integration Server, and thousands of servers like it.
Across the catalogue