AI agents call boundary_detail 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.
The 'boundary_detail' suffix pattern in this ATTOM real estate API server aligns with other _detail tools on the same server that fetch specific property information. The absence of create/update/delete/execute verbs and the lack of destructive or financial indicators suggests this retrieves boundary data only.
From the tool's definition Tool name 'boundary_detail' suggests querying property boundary information. The empty description limits specificity, but contextual evidence from sibling tools (assessment_detail, avm_detail, building_permits) which are all Read operations on real estate…
Attacks that exploit this kind of access
boundary_detail. 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 boundary_detail: 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.
boundary_detail 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 boundary_detail 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 boundary_detail. 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.
boundary_detail 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 →