AI agents use update_investigation 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.
This tool modifies investigation records reversibly without deleting or destroying data. While it operates on security investigation data (which is sensitive), the impact is limited to updating investigation details/status rather than executing code, triggering external operations, or causing financial transactions.
From the tool's definition Tool name 'update_investigation' and description 'Update an existing investigation' indicate modification of existing data within the InsightIDR SIEM.
Attacks that exploit this kind of access
Update an existing investigation. 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.
Register the Rapid7 MCP server in PolicyLayer and add a rule for update_investigation: 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.
update_investigation is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the update_investigation 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.
Set action: deny in the PolicyLayer policy for update_investigation. 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.
update_investigation 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.
Every MCP server has a record like this.
Type a name, get the same breakdown: verified identity, auth posture, risk grade, capabilities, recommended policy.
Teams ship this data inside their own products. See what a licence covers →