create_saved_query · Rapid7 MCP: Risk & Policy

WHAT IT DOES

What create_saved_query does on Rapid7

AI agents use create_saved_query to create or update resources in Rapid7 — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Rapid7 environment.

WHY IT NEEDS A POLICY

Why create_saved_query needs a policy

This tool creates and stores a new saved query configuration, which is a reversible write operation. The stored query itself does not execute or retrieve data directly—it only persists query metadata for later reuse. A misused saved query creates minor risk: it may clutter the query library or expose query logic to other users, but cannot delete data, execute arbitrary code, or cause financial harm.

From the tool's definition Tool name 'create_saved_query' and description 'Save a LEQL query for reuse in InsightIDR' indicate creation and storage of a query definition that persists for future use.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

create_saved_query Rate-limited

create_saved_query 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": {
    "create_saved_query": {
      "limits": [
        {
          "counter": "create_saved_query_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 Rapid7, so you can run agents against it safely.

FAQ

Questions about create_saved_query

What does the create_saved_query tool do? +

Save a LEQL query for reuse in InsightIDR. It is categorised as a Write tool in the Rapid7 MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.

How do I enforce a policy on create_saved_query? +

Register the Rapid7 MCP server in PolicyLayer and add a rule for create_saved_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 Rapid7. Nothing to install.

What risk level is create_saved_query? +

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

Can I rate-limit create_saved_query? +

Yes. Add a rate_limit block to the create_saved_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 create_saved_query completely? +

Set action: deny in the PolicyLayer policy for create_saved_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 create_saved_query? +

create_saved_query is provided by the Rapid7 MCP server (solomonneas/rapid7-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.