AI agents use book_walk to commit financial operations through Mcp Wag — usually the final step of a payment, billing, or trading workflow. A call moves real money.
Booking a dog walking session commits a financial obligation (payment for the service). This is a transactional action that initiates a purchase/booking of a paid pet care service, making it Financial. The severity is high because an AI agent could book (and charge for) sessions without explicit user confirmation, and recurring or multiple bookings could result in significant financial exposure.
From the tool's definition Book a dog walking session on wagwalking.com
Attacks that exploit this kind of access
Book a dog walking session on wagwalking.com. Requires WAG_EMAIL and WAG_PASSWORD environment variables to be set. It is categorised as a Financial tool in the Mcp Wag MCP Server, which means it involves financial transactions. Block by default and require explicit approval.
Register the Mcp Wag MCP server in PolicyLayer and add a rule for book_walk: 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 Mcp Wag. Nothing to install.
book_walk 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 book_walk 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 book_walk. 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.
book_walk is provided by the Mcp Wag MCP server (markswendsen-code/mcp-wag). 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 →