Verify an independently verified evidence record
AI agents call verify_evidence to retrieve information from Lilo Vacation Rentals without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves and validates evidence records already in the system. It performs a lookup/verification check on data that has been independently verified, consistent with a Read operation. There is no indication that it modifies data, executes commands, deletes records, or moves funds.
From the tool's definition Tool name 'verify_evidence' and description 'Verify an independently verified evidence record' indicate querying or validation of existing data without modification or execution of code.
Attacks that exploit this kind of access
Verify an independently verified evidence record. It is categorised as a Read tool in the Lilo Vacation Rentals MCP Server, which means it retrieves data without modifying state.
Register the Lilo Vacation Rentals MCP server in PolicyLayer and add a rule for verify_evidence: 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 Lilo Vacation Rentals. Nothing to install.
verify_evidence 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 verify_evidence 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 verify_evidence. 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.
verify_evidence is provided by the Lilo Vacation Rentals MCP server (lilo-property/mcp-server). 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 →