NYC HPD housing violations. Filter by bbl or address, classCode (A=least severe through C=immediately hazardous), currentStatusOnly=true (open violations). Returns full address + apartment + story, inspection + certify-by + correct-by dates, current status, NOV narrative.
AI agents call property.nyc-violations to retrieve information from Mcp without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool queries and retrieves public housing violation records. While the data may be sensitive to property owners, the operation is read-only with no side effects, no code execution, and no ability to modify or delete data. The severity is low because misuse would only expose or aggregate existing public regulatory information, not cause direct harm or financial impact.
From the tool's definition Tool retrieves and filters NYC HPD housing violations data by bbl, address, classCode, and status. Returns inspection dates, violation narratives, and correction deadlines. No modification, deletion, execution, or financial operation is performed.
Attacks that exploit this kind of access
NYC HPD housing violations. Filter by bbl or address, classCode (A=least severe through C=immediately hazardous), currentStatusOnly=true (open violations). Returns full address + apartment + story, inspection + certify-by + correct-by dates, current status, NOV narrative. It is categorised as a Read tool in the Mcp MCP Server, which means it retrieves data without modifying state.
Register the MCP server in PolicyLayer and add a rule for property.nyc-violations: 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 Mcp. Nothing to install.
property.nyc-violations 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 property.nyc-violations 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 property.nyc-violations. 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.
property.nyc-violations is provided by the MCP server (@2sio/mcp). 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 →