Audit recurring subscriptions: total monthly spend, biggest line items, what renews soon. Also add/cancel.
AI agents use subscriptions_audit to commit financial operations through Personal Brain — usually the final step of a payment, billing, or trading workflow. A call moves real money.
The tool explicitly supports adding and cancelling recurring subscriptions, which are financial obligations. Cancellation is an irreversible or consequential financial action, and the tool directly manages monetary commitments. This places it firmly in the Financial category with high severity due to the potential to cancel or add subscriptions without user confirmation.
From the tool's definition 'cancel' subscriptions and 'total monthly spend' — the tool can cancel financial commitments and audits recurring financial obligations
Attacks that exploit this kind of access
Audit recurring subscriptions: total monthly spend, biggest line items, what renews soon. Also add/cancel. It is categorised as a Financial tool in the Personal Brain MCP Server, which means it involves financial transactions. Block by default and require explicit approval.
Register the Personal Brain MCP server in PolicyLayer and add a rule for subscriptions_audit: 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 Personal Brain. Nothing to install.
subscriptions_audit 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 subscriptions_audit 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 subscriptions_audit. 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.
subscriptions_audit is provided by the Personal Brain MCP server (phantomts/personal-brain-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 →