AI agents use schedule_recurring to commit financial operations through Mcp Wag — usually the final step of a payment, billing, or trading workflow. A call moves real money.
Scheduling a recurring service with a pet care platform creates ongoing financial obligations (repeated payments for each walk session). This falls squarely in the Financial category, and because it is recurring rather than one-time, the blast radius is high — an AI agent misusing this tool could commit the user to many future charges that are difficult to reverse.
From the tool's definition Set up a recurring dog walking schedule — recurring bookings imply repeated financial commitments/charges over time on wagwalking.com
Attacks that exploit this kind of access
Set up a recurring dog walking schedule with a specific walker on wagwalking.com. Requires WAG_EMAIL and WAG_PASSWORD. 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 schedule_recurring: 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.
schedule_recurring 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 schedule_recurring 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 schedule_recurring. 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.
schedule_recurring 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 →