AI agents call verify_receipt to retrieve information from ProofSlip without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool performs a read-only operation: it fetches the full data associated with a receipt (type, status, summary, payload, ref, expiry) for verification purposes. There are no side effects, no state changes, and no destructive or financial operations. The only potential risk is exposure of sensitive data within the receipt payload, but the tool itself is fundamentally a retrieval mechanism.
From the tool's definition Tool retrieves receipt data and status information without modifying or deleting anything. The description states it 'verify' and 'retrieve' — pure read operations that query the state of an existing receipt object.
Attacks that exploit this kind of access
Verify a ProofSlip receipt and retrieve its full data (type, status, summary, payload, ref, expiry). It is categorised as a Read tool in the ProofSlip MCP Server, which means it retrieves data without modifying state.
Register the ProofSlip MCP server in PolicyLayer and add a rule for verify_receipt: 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 ProofSlip. Nothing to install.
verify_receipt 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 verify_receipt 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 verify_receipt. 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.
verify_receipt is provided by the ProofSlip MCP server (@proofslip/mcp-server). 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 →