AI agents use create_checkout to create or update resources in Paymongo — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Paymongo environment.
This tool creates (writes) a new checkout session, which is a reversible operation—the session can be cancelled or left unused. It does not charge money directly (that would require separate payment execution), does not delete data, and does not execute arbitrary code. However, severity is high because misuse could create fraudulent checkout sessions, customer confusion, or abuse of payment infrastructure.
From the tool's definition Tool name 'create_checkout' and description 'Create a hosted checkout session (returns a checkout URL)' indicate creation of a new checkout resource. Combined with server context (PayMongo payment gateway), this creates a payment session.
Attacks that exploit this kind of access
Create a hosted checkout session (returns a checkout URL). It is categorised as a Write tool in the Paymongo MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Paymongo MCP server in PolicyLayer and add a rule for create_checkout: 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 Paymongo. Nothing to install.
create_checkout is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the create_checkout 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_checkout. 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_checkout is provided by the Paymongo MCP server (theyahia/paymongo-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 →