AI agents use browse_and_buy 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 commits financial obligations by completing purchases with a real payment instrument (Lithic virtual card). It is fully autonomous (browse, add to cart, checkout) and could be misused by an AI agent to make unauthorized purchases. Financial is the highest severity category, and the blast radius is critical given it can spend real money without further confirmation steps.
From the tool's definition 'complete purchase using a Lithic virtual card' — the tool autonomously browses, adds items to cart, and executes a real financial transaction using a virtual payment card.
Attacks that exploit this kind of access
Browse an online store, add items to cart, and complete purchase using a Lithic virtual card. Requires Playwright installed. 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 browse_and_buy: 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.
browse_and_buy 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 browse_and_buy 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 browse_and_buy. 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.
browse_and_buy 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 →