AI agents call prmaat_audit_proof 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 retrieves cryptographic proof data from an audit log without modifying, deleting, or executing any operations. It is a query mechanism for verification purposes, fitting the Read category (retrieves or queries data; no side effects).
From the tool's definition Tool name 'prmaat_audit_proof' and description 'Fetch a Merkle membership proof for an audit-log row' indicate a retrieval operation. The verb 'Fetch' and the action of 'proving' membership in an audit log are read-only operations with no side effects.
Attacks that exploit this kind of access
Fetch a Merkle membership proof for an audit-log row, proving it. 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_audit_proof: 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_audit_proof 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_audit_proof 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_audit_proof. 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_audit_proof 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 →