execute_insights_query · Observability MCP: Risk & Policy

WHAT IT DOES

What execute_insights_query does on Observability

AI agents invoke execute_insights_query to trigger actions in Observability. 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_insights_query needs a policy

This tool runs arbitrary SQL queries in BigQuery, making it an Execute category tool. While the name suggests read-only 'insights', the mechanism is code execution whose effects depend entirely on the SQL provided.

From the tool's definition Tool executes BigQuery SQL queries against datasets. The description states it 'Executes a BigQuery SQL query' which is code execution. SQL queries can modify data, exfiltrate sensitive information, or consume significant resources depending on arguments.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

execute_insights_query Rate-limited

execute_insights_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.

View as policy code

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "execute_insights_query": {
      "limits": [
        {
          "counter": "execute_insights_query_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 Observability, so you can run agents against it safely.

FAQ

Questions about execute_insights_query

What does the execute_insights_query tool do? +

Executes a BigQuery SQL query against an insights dataset and returns the result. It is categorised as a Execute tool in the Observability 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_insights_query? +

Register the Observability MCP server in PolicyLayer and add a rule for execute_insights_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 Observability. Nothing to install.

What risk level is execute_insights_query? +

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

Can I rate-limit execute_insights_query? +

Yes. Add a rate_limit block to the execute_insights_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.

How do I block execute_insights_query completely? +

Set action: deny in the PolicyLayer policy for execute_insights_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.

What MCP server provides execute_insights_query? +

execute_insights_query is provided by the Observability MCP server (@google-cloud/observability-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.