run_insights_query · Cloudwatch MCP: Risk & Policy

WHAT IT DOES

What run_insights_query does on Cloudwatch

AI agents invoke run_insights_query to trigger actions in Cloudwatch. 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 run_insights_query needs a policy

This tool runs/executes a query against AWS CloudWatch Logs Insights. While the server description states read-only access and the tool is used for aggregation/counting, it actively executes operations against an external AWS service rather than simply retrieving pre-existing data.

From the tool's definition 'Run a CloudWatch Logs Insights query' — actively executes a query against AWS CloudWatch Logs infrastructure

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

run_insights_query Rate-limited

run_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": {
    "run_insights_query": {
      "limits": [
        {
          "counter": "run_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 Cloudwatch, so you can run agents against it safely.

FAQ

Questions about run_insights_query

What does the run_insights_query tool do? +

Run a CloudWatch Logs Insights query over one or more log groups (best for counting/aggregation — e.g. count occurrences, distinct instances). Provide either logGroupName or logGroupNames. It is categorised as a Execute tool in the Cloudwatch MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on run_insights_query? +

Register the Cloudwatch MCP server in PolicyLayer and add a rule for run_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 Cloudwatch. Nothing to install.

What risk level is run_insights_query? +

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

Can I rate-limit run_insights_query? +

Yes. Add a rate_limit block to the run_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 run_insights_query completely? +

Set action: deny in the PolicyLayer policy for run_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 run_insights_query? +

run_insights_query is provided by the Cloudwatch MCP server (shivam-singh-au17/cloudwatch-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.