execute_bigquery_sql · MCP BigQuery Server MCP

WHAT IT DOES

What execute_bigquery_sql does on MCP BigQuery Server

AI agents invoke execute_bigquery_sql to trigger actions in MCP BigQuery 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.

WHY IT NEEDS A POLICY

Why execute_bigquery_sql needs a policy

Although the description claims the tool executes 'read-only' queries, the tool is classified as Execute rather than Read because: (1) it explicitly performs SQL query execution, which is code execution, not mere data retrieval; (2) even 'read-only' SQL queries on BigQuery can have side effects (e.g., consuming quota, triggering external operations via UDFs, or accessing sensitive data based on dynamic filters); (3)…

From the tool's definition Tool name is 'execute_bigquery_sql' and description states it 'Execute[s] a read-only SQL query on BigQuery'.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

execute_bigquery_sql Rate-limited

execute_bigquery_sql 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.

View as policy code

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "execute_bigquery_sql": {
      "limits": [
        {
          "counter": "execute_bigquery_sql_rate",
          "window": "minute",
          "max": 10,
          "scope": "grant"
        }
      ]
    }
  }
}

RATE-LIMIT THIS TOOL →

Instant setup, no code required.

PolicyLayer is an MCP gateway: every tool call is checked against your rule before it reaches MCP BigQuery Server, so you can run agents against it safely.

FAQ

Questions about execute_bigquery_sql

What does the execute_bigquery_sql tool do? +

Execute a read-only SQL query on BigQuery with intelligent caching, performance tracking, and automatic schema detection. It is categorised as a Execute tool in the MCP BigQuery Server MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on execute_bigquery_sql? +

Register the MCP BigQuery Server MCP server in PolicyLayer and add a rule for execute_bigquery_sql: 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 MCP BigQuery Server. Nothing to install.

What risk level is execute_bigquery_sql? +

execute_bigquery_sql is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.

Can I rate-limit execute_bigquery_sql? +

Yes. Add a rate_limit block to the execute_bigquery_sql 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.

How do I block execute_bigquery_sql completely? +

Set action: deny in the PolicyLayer policy for execute_bigquery_sql. 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.

What MCP server provides execute_bigquery_sql? +

execute_bigquery_sql is provided by the MCP BigQuery Server MCP server (mousten/mcp-bigquery-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.