AI agents call prmaat_verify to retrieve information from Prmaat without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool performs verification/validation of a DID (Decentralized Identifier) by querying its status and properties. It retrieves information (passport existence, name) with no side effects, modifications, or external execution. This is a classic Read operation — similar to a lookup or GET request.
From the tool's definition Tool name is 'prmaat_verify' and description indicates it 'Verify a PrMaat DID. Returns whether the passport exists, its name' — the verb 'Verify' and 'Returns' indicate a query operation that retrieves and validates existing identity data without…
Attacks that exploit this kind of access
Verify a PrMaat DID. Returns whether the passport exists, its name,. It is categorised as a Read tool in the Prmaat MCP Server, which means it retrieves data without modifying state.
Register the Prmaat MCP server in PolicyLayer and add a rule for prmaat_verify: 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 Prmaat. Nothing to install.
prmaat_verify 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 prmaat_verify 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 prmaat_verify. 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.
prmaat_verify is provided by the Prmaat MCP server (prmaat/mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
prmaat_verify is one line of Prmaat's registry record.
The record carries the whole server: verified identity, auth posture, risk grade, every tool classified, recommended policy — re-checked continuously.
Teams ship this data inside their own products. See what a licence covers →