AI agents call discover_property to retrieve information from Homedata without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
Based on the pattern of sibling tools which are all Read operations querying property data, and the generic 'discover' verb which typically indicates search/retrieval, this tool is classified as Read. Confidence is moderate (0.75) rather than high because the tool description is empty, creating some ambiguity about its true function. No evidence of data modification, deletion, or financial operations.
From the tool's definition Tool name 'discover_property' with no description provided. Context shows the server queries UK property data (EPCs, sales history, planning, flood risk, council tax, demographics). Sibling tools are all Read operations (get_*, check_*, batch_lookup).
Attacks that exploit this kind of access
discover_property. It is categorised as a Read tool in the Homedata MCP Server, which means it retrieves data without modifying state.
Register the Homedata MCP server in PolicyLayer and add a rule for discover_property: 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 Homedata. Nothing to install.
discover_property 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 discover_property 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 discover_property. 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.
discover_property is provided by the Homedata MCP server (wehomemove/homedata-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 →