save_query_result · Bq MCP: Risk & Policy

WHAT IT DOES

What save_query_result does on Bq

AI agents use save_query_result to create or update resources in Bq — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Bq environment.

WHY IT NEEDS A POLICY

Why save_query_result needs a policy

With an empty description, I rely on the tool name and context. 'save_query_result' implies creating/writing output files or persisting results, which is reversible (Write category). The lack of description lowers confidence slightly. Severity is medium because while file writes are generally safe, they could fill storage or overwrite important data depending on permissions and arguments.

From the tool's definition Tool name is 'save_query_result' and sibling tools include 'execute_query', indicating this tool creates or persists data from query results. The server description mentions 'file export' capability.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

save_query_result Rate-limited

save_query_result stays usable, but capped — an agent stuck in a loop can't make hundreds of changes a minute. Everything else on the server is denied unless you say otherwise.

View as policy code

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "save_query_result": {
      "limits": [
        {
          "counter": "save_query_result_rate",
          "window": "minute",
          "max": 30,
          "scope": "grant"
        }
      ]
    }
  }
}

LIMIT THIS TOOL →

Instant setup, no code required.

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

FAQ

Questions about save_query_result

What does the save_query_result tool do? +

save_query_result. It is categorised as a Write tool in the Bq MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.

How do I enforce a policy on save_query_result? +

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

What risk level is save_query_result? +

save_query_result is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.

Can I rate-limit save_query_result? +

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

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

save_query_result is provided by the Bq MCP server (takada-at/bq_mcp_server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.