AI agents call prmaat_me 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 fetches and returns the current user's authentication credential (passport). It is a read-only operation that retrieves data without modifying state, triggering external actions, or deleting anything. The blast radius of misuse is minimal—an agent obtaining the user's passport information represents information disclosure but not further compromise of other systems or destructive action.
From the tool's definition Tool name 'prmaat_me' and description 'Return the authenticated passport' indicate retrieval of identity/authentication information with no modification or side effects.
Attacks that exploit this kind of access
Return the authenticated passport. 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_me: 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_me 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_me 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_me. 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_me 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.
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 →