AI agents call neighborhood_community 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 neighborhood or community data from a real estate database based on context. This is a read operation with no side effects. Severity is medium because unauthorized access to detailed real estate and neighborhood data could enable stalking, harassment, or targeted crimes, but it does not directly enable financial fraud, system compromise, or destruction.
From the tool's definition Tool is part of ATTOM real estate API server which 'exposes property details, valuations, assessments, sales, and area data via natural language.' Sibling tools like 'assessment_snapshot', 'avm_snapshot', and 'boundary_detail' are clearly read operations.
Attacks that exploit this kind of access
neighborhood_community. 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 neighborhood_community: 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.
neighborhood_community 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 neighborhood_community 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 neighborhood_community. 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.
neighborhood_community 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 →