query_bigquery · Gcp MCP: Risk & Policy

WHAT IT DOES

What query_bigquery does on Gcp

AI agents invoke query_bigquery to trigger actions in Gcp. 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 query_bigquery needs a policy

Executing arbitrary SQL can read, modify, or destroy data depending on the query (SELECT, INSERT, UPDATE, DELETE, DROP, etc.). Since the tool permits arbitrary SQL execution, it falls under Execute (and could be Destructive if DDL/DML is allowed). The blast radius is high because a malicious or erroneous query could exfiltrate large datasets, corrupt tables, or drop schemas.

From the tool's definition "Execute a BigQuery SQL query" — the tool runs arbitrary SQL against BigQuery.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

query_bigquery Rate-limited

query_bigquery 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": {
    "query_bigquery": {
      "limits": [
        {
          "counter": "query_bigquery_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 Gcp, so you can run agents against it safely.

FAQ

Questions about query_bigquery

What does the query_bigquery tool do? +

Execute a BigQuery SQL query. It is categorised as a Execute tool in the Gcp MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on query_bigquery? +

Register the Gcp MCP server in PolicyLayer and add a rule for query_bigquery: 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 Gcp. Nothing to install.

What risk level is query_bigquery? +

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

Can I rate-limit query_bigquery? +

Yes. Add a rate_limit block to the query_bigquery 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 query_bigquery completely? +

Set action: deny in the PolicyLayer policy for query_bigquery. 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 query_bigquery? +

query_bigquery is provided by the Gcp MCP server (lokimcpuniverse/gcp-mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.