Send a physical postcard that will be printed and shipped to a real address. Delivery takes 5-10 business days.
AI agents use send_postcard to commit financial operations through Postcardbot — usually the final step of a payment, billing, or trading workflow. A call moves real money.
Sending a physical postcard incurs a real monetary cost per card (starting at $0.72/card). Each invocation commits a financial obligation for printing and mailing. This is a Financial category action with high severity since an AI agent could send large numbers of postcards, accumulating significant charges.
From the tool's definition Send a physical postcard that will be printed and shipped to a real address... volume pricing from $0.72/card
Attacks that exploit this kind of access
Send a physical postcard that will be printed and shipped to a real address. Delivery takes 5-10 business days. It is categorised as a Financial tool in the Postcardbot MCP Server, which means it involves financial transactions. Block by default and require explicit approval.
Register the Postcardbot MCP server in PolicyLayer and add a rule for send_postcard: 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 Postcardbot. Nothing to install.
send_postcard 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 send_postcard 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 send_postcard. 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.
send_postcard is provided by the Postcardbot MCP server (postcardbot/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 →