AI agents use send_email to commit financial operations through X402mail — usually the final step of a payment, billing, or trading workflow. A call moves real money.
The server description explicitly states that emails are sent with USDC micropayments. Therefore, invoking send_email likely triggers a financial transaction (spending USDC) in addition to sending a message. Per the rules, Financial is the most severe applicable category. Confidence is moderate because the tool description itself is empty, but the server context strongly implies financial consequences.
From the tool's definition Tool name 'send_email' on server 'x402mail' described as 'send and receive email with USDC micropayments' — sending email on this server involves USDC micropayments, making it a financial operation.
Attacks that exploit this kind of access
send_email. It is categorised as a Financial tool in the X402mail MCP Server, which means it involves financial transactions. Block by default and require explicit approval.
Register the X402mail MCP server in PolicyLayer and add a rule for send_email: 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 X402mail. Nothing to install.
send_email 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_email 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_email. 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_email is provided by the X402mail MCP server (muzsailajos/x402mail). 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 →