create_payment_intent
AI agents use create_payment_intent to commit financial operations through Green Helix — usually the final step of a payment, billing, or trading workflow. A call moves real money.
Payment intent creation directly commits or prepares financial transactions. Even with an empty description, the tool name and server context (AI agent commerce platform with explicit payment/escrow capabilities) make this a Financial category tool. Misuse by an AI agent could result in unauthorized charges or financial commitments. Critical severity due to potential for direct monetary harm.
From the tool's definition Tool name 'create_payment_intent' in a commerce platform context with sibling tools including 'create_refund', 'create_subscription', 'get_balance', 'list_charges', and 'list_invoices'.
Attacks that exploit this kind of access
create_payment_intent. 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_payment_intent: 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_payment_intent 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_payment_intent 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_payment_intent. 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_payment_intent 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 →