AI agents use pay to commit financial operations through ClawPay — usually the final step of a payment, billing, or trading workflow. A call moves real money.
This tool directly moves money by creating and confirming payments across real payment processors. Even with single-use virtual cards, a payment that is confirmed commits a financial obligation and transfers funds. This is the most severe category - Financial > Destructive > Execute > Write > Read. Misuse by an AI agent could result in unauthorized charges, fraud, or significant financial loss to users.
From the tool's definition The tool creates and confirms a payment - explicit financial transaction. The description states it connects to payment processors (Lithic, Stripe, PayPal) for 'automated shopping', and the tool 'Create[s] and confirm[s] a payment'.
Attacks that exploit this kind of access
Create and confirm a payment in cents. It is categorised as a Financial tool in the ClawPay MCP Server, which means it involves financial transactions. Block by default and require explicit approval.
Register the ClawPay MCP server in PolicyLayer and add a rule for pay: 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 ClawPay. Nothing to install.
pay is a Financial tool with critical risk. Critical-risk tools should be blocked by default and only enabled with explicit human approval.
Yes. Add a rate_limit block to the pay 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 pay. 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.
pay is provided by the ClawPay MCP server (xodn348/clawpay). 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 →