AI agents call preforeclosure_details to retrieve information from Attom without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool appears to retrieve pre-foreclosure property details—a read operation with no side effects. However, confidence is reduced due to the empty description. Severity is medium because pre-foreclosure data is sensitive financial/personal information that could enable harassment, discrimination, or predatory targeting if misused by an agent, despite being read-only in nature.
From the tool's definition Tool name 'preforeclosure_details' and server context indicate retrieval of pre-foreclosure property information from ATTOM's real estate API. Description is empty, limiting precision.
Attacks that exploit this kind of access
preforeclosure_details. It is categorised as a Read tool in the Attom MCP Server, which means it retrieves data without modifying state.
Register the Attom MCP server in PolicyLayer and add a rule for preforeclosure_details: 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 Attom. Nothing to install.
preforeclosure_details 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 preforeclosure_details 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 preforeclosure_details. 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.
preforeclosure_details is provided by the Attom MCP server (nkbud/mcp-server-attom). 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 →