Send the same postcard to multiple recipients (async). Same message, image, and return address
AI agents use bulk_send to commit financial operations through Postcardbot — usually the final step of a payment, billing, or trading workflow. A call moves real money.
This tool directly commits financial obligations by sending physical postcards to up to 500 recipients at a per-card cost. A misuse could result in charges of up to ~$360 per bulk send operation. It triggers real-world physical mail delivery, making it both financially impactful and practically irreversible once sent.
From the tool's definition Send the same postcard to multiple recipients... up to 500 recipients... volume pricing from $0.72/card
Risk signalsBulk/mass operation — affects multiple targets
Attacks that exploit this kind of access
Send the same postcard to multiple recipients (async). Same message, image, and return address. 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 bulk_send: 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.
bulk_send 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 bulk_send 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 bulk_send. 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.
bulk_send 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 →