Bank-statement-style merged feed of payments sent (direction:
AI agents use payments_activity to commit financial operations through Mailgent MCP Server — usually the final step of a payment, billing, or trading workflow. A call moves real money.
The tool surfaces financial payment data (bank-statement-style feed of payments sent), placing it firmly in the Financial category. While it appears to be a read/query operation (activity feed), it exposes sensitive financial transaction data. Severity is high because misuse could expose confidential payment history and financial flows.
From the tool's definition 'payments_activity' with 'Bank-statement-style merged feed of payments sent' — directly relates to financial payment transactions
Attacks that exploit this kind of access
Bank-statement-style merged feed of payments sent (direction:. It is categorised as a Financial tool in the Mailgent MCP Server MCP Server, which means it involves financial transactions. Block by default and require explicit approval.
Register the Mailgent MCP Server MCP server in PolicyLayer and add a rule for payments_activity: 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 Mailgent MCP Server. Nothing to install.
payments_activity 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 payments_activity 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 payments_activity. 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.
payments_activity is provided by the Mailgent MCP Server MCP server (loomal-ai/loomal-mcp). 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 →