AI agents call search_address 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.
search_address most likely retrieves or queries address/property information without modifying data. The server is designed for querying UK property data via API, and all documented sibling tools perform read-only retrieval. No indication of write, destructive, execute, or financial operations.
From the tool's definition Tool name 'search_address' and server context indicating query-based UK property data access. Description is empty but sibling tools (get_comparables, get_crime, get_demographics, get_planning_applications, get_postcode_profile, get_property_sales) are all…
Attacks that exploit this kind of access
search_address. 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 search_address: 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.
search_address 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 search_address 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 search_address. 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.
search_address 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 →