create_subscription
AI agents use create_subscription to commit financial operations through Green Helix — usually the final step of a payment, billing, or trading workflow. A call moves real money.
On a payments/commerce platform, 'create_subscription' almost certainly sets up a recurring billing arrangement, which constitutes committing a financial obligation. The sibling tools (create_payment_intent, create_refund, list_charges) confirm this is a payments-focused server. Empty description lowers confidence slightly, but context is strong. Financial is the highest severity category and applies here.
From the tool's definition Tool name 'create_subscription' on a server described as an 'AI agent commerce platform' with sibling tools including 'create_payment_intent', 'create_refund', and 'list_charges' — all financial operations.
Attacks that exploit this kind of access
create_subscription. It is categorised as a Financial tool in the Green Helix MCP Server, which means it involves financial transactions. Block by default and require explicit approval.
Register the Green Helix MCP server in PolicyLayer and add a rule for create_subscription: 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 Green Helix. Nothing to install.
create_subscription 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 create_subscription 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 create_subscription. 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.
create_subscription is provided by the Green Helix MCP server (mirni/a2a). 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 →