stamp_duty
AI agents call stamp_duty to retrieve information from UK Property Intelligence without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
Given the tool name references stamp duty (a tax calculation/lookup function) and sits alongside other informational tools like property_report and company_search, it most likely retrieves or calculates stamp duty rates/amounts rather than modifying data or executing arbitrary operations. The empty description reduces confidence, but the naming pattern and context strongly suggest a Read operation.
From the tool's definition Tool named 'stamp_duty' with empty description. Based on context, this appears to be a lookup/calculation tool for UK stamp duty information, consistent with other Read tools on the server (property_report, company_search, planning_search).
Attacks that exploit this kind of access
stamp_duty. It is categorised as a Read tool in the UK Property Intelligence MCP Server, which means it retrieves data without modifying state.
Register the UK Property Intelligence MCP server in PolicyLayer and add a rule for stamp_duty: 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 UK Property Intelligence. Nothing to install.
stamp_duty 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 stamp_duty 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 stamp_duty. 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.
stamp_duty is provided by the UK Property Intelligence MCP server (paulieb89/uk-property-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 →