AI agents use create_receipt to create or update resources in ProofSlip — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your ProofSlip environment.
The tool creates a new receipt object to record an event within a verification system. This is a Write action (creates data) rather than Read (no retrieval), Destructive (data is not deleted), Execute (no external commands/code), Financial (no money movement), or Other.
From the tool's definition Tool name 'create_receipt' and description 'Create a ProofSlip receipt to record that something happened' indicate creation of a new object, which is a reversible Write operation.
Attacks that exploit this kind of access
Create a ProofSlip receipt to record that something happened. It is categorised as a Write tool in the ProofSlip MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the ProofSlip MCP server in PolicyLayer and add a rule for create_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.
create_receipt is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the create_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 create_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.
create_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 →