AI agents call rental_avm 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 retrieves valuation estimates for rental properties without side effects. It is a data query operation similar to sibling tools (avm_detail, avm_snapshot, assessment_detail) that fetch property information. No financial transactions, code execution, data modification, or destructive actions are performed.
From the tool's definition Tool name 'rental_avm' and description 'Get rental AVM information' indicate a retrieval operation. AVM (Automated Valuation Model) data is queried/retrieved with no modification, deletion, or execution of external operations.
Attacks that exploit this kind of access
Get rental AVM information. 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 rental_avm: 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.
rental_avm 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 rental_avm 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 rental_avm. 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.
rental_avm 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 →