AI agents call hierarchy_lookup 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 tool appears to retrieve hierarchical data (likely property classifications or geographic boundaries) from ATTOM's database. With no modifying, destructive, or financial operations evident, and consistent with sibling read-only tools on the server, this is classified as Read. Confidence is moderate (0.75) due to empty description—if it unexpectedly performs writes or executes code, severity would increase.
From the tool's definition Tool name 'hierarchy_lookup' and sibling tools (assessment_detail, avm_detail, boundary_detail) all suggest data retrieval from ATTOM's real estate API. No description provided, but naming pattern indicates a lookup/query operation.
Attacks that exploit this kind of access
hierarchy_lookup. 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 hierarchy_lookup: 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.
hierarchy_lookup 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 hierarchy_lookup 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 hierarchy_lookup. 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.
hierarchy_lookup 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 →