NYC DOB construction permits. Filter by bbl or address, jobType (A1/A2/A3/NB/DM/etc.), permitStatus (ISSUED/IN PROCESS/etc.). Returns job + permit IDs, work type, building type, residential flag, filing/issuance/expiration dates, estimated fee.
AI agents call property.nyc-permits 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 purely queries and retrieves public NYC Department of Buildings permit information. It performs no side effects, modifications, or irreversible actions. The data returned (permit IDs, dates, fees, building classifications) are informational only.
From the tool's definition Tool description explicitly states it filters and returns permit data: 'Filter by bbl or address, jobType...permitStatus...Returns job + permit IDs, work type, building type, residential flag, filing/issuance/expiration dates, estimated fee.' All operations…
Attacks that exploit this kind of access
NYC DOB construction permits. Filter by bbl or address, jobType (A1/A2/A3/NB/DM/etc.), permitStatus (ISSUED/IN PROCESS/etc.). Returns job + permit IDs, work type, building type, residential flag, filing/issuance/expiration dates, estimated fee. 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-permits: 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-permits 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-permits 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-permits. 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-permits 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 →