AI agents call postio_udprn_lookup to retrieve information from Postio without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves delivery point information by UDPRN (Unique Delivery Point Reference Number) without any side effects. It is a simple lookup against a reference database with no ability to modify, delete, or trigger external actions. The risk is minimal—an AI agent using this tool cannot cause harm beyond potentially discovering valid UK addresses, which is already public Royal Mail data.
From the tool's definition Tool name 'postio_udprn_lookup' and description 'Look up a single UK delivery point' indicate a read-only query operation against Royal Mail PAF data. No modification, deletion, execution, or financial transaction capability is described.
Attacks that exploit this kind of access
Look up a single UK delivery point by its UDPRN (Royal Mail. It is categorised as a Read tool in the Postio MCP Server, which means it retrieves data without modifying state.
Register the Postio MCP server in PolicyLayer and add a rule for postio_udprn_lookup: 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 Postio. Nothing to install.
postio_udprn_lookup 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 postio_udprn_lookup 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 postio_udprn_lookup. 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.
postio_udprn_lookup is provided by the Postio MCP server (postio-uk/postio-integrations). 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 →