AI agents call get_asset to retrieve information from Rapid7 without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool queries and retrieves existing asset information (software inventory, vulnerabilities, network configuration) from the SIEM. It performs read-only operations. Severity is medium because asset details including vulnerabilities and network interfaces could be sensitive security information that an AI agent could misuse to plan attacks, but the tool itself is not destructive or executable.
From the tool's definition Tool name is 'get_asset' and description states it retrieves 'full details of an InsightIDR asset including installed software, vulnerabilities, and network interfaces' — purely a data retrieval operation with no side effects.
Attacks that exploit this kind of access
Get full details of an InsightIDR asset including installed software, vulnerabilities, and network interfaces. It is categorised as a Read tool in the Rapid7 MCP Server, which means it retrieves data without modifying state.
Register the Rapid7 MCP server in PolicyLayer and add a rule for get_asset: 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.
get_asset is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the get_asset 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 get_asset. 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.
get_asset 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 →