AI agents use create_payment to commit financial operations through Tabby — usually the final step of a payment, billing, or trading workflow. A call moves real money.
This tool directly moves money or commits financial obligations by creating a payment transaction on the Tabby BNPL (Buy Now Pay Later) platform. Even though it operates on an 'approved session,' creating a payment is a financial commitment that cannot be easily undone.
From the tool's definition Tool name is 'create_payment' and server description explicitly states it 'Enables interaction with Tabby BNPL platform for managing checkout sessions, payments, captures, refunds, and voids.' The tool creates a payment, which commits financial obligations on…
Attacks that exploit this kind of access
Create a payment from an approved session. It is categorised as a Financial tool in the Tabby MCP Server, which means it involves financial transactions. Block by default and require explicit approval.
Register the Tabby MCP server in PolicyLayer and add a rule for create_payment: 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 Tabby. Nothing to install.
create_payment 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 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. 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 is provided by the Tabby MCP server (theyahia/tabby-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 →