Prepare a manual checkout URL for a Sanka Buy merchant purchase after Purchase Order creation. This does not complete payment.
AI agents use prepare_buy_checkout to create or update resources in Sanka MCP Server — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Sanka MCP Server environment.
The tool prepares checkout infrastructure (URL generation) rather than executing payment or transferring funds, making it Write rather than Financial. However, it sits in the payment flow and could be misused to prepare fraudulent checkouts. Severity is medium because while it creates checkout state, payment completion is blocked and the actual financial transaction requires additional steps.
From the tool's definition Tool name 'prepare_buy_checkout' and description indicates it prepares a checkout URL for a merchant purchase after PO creation. The description explicitly states 'This does not complete payment', confirming no financial transaction is executed.
Attacks that exploit this kind of access
Prepare a manual checkout URL for a Sanka Buy merchant purchase after Purchase Order creation. This does not complete payment. It is categorised as a Write tool in the Sanka MCP Server MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Sanka MCP Server MCP server in PolicyLayer and add a rule for prepare_buy_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 Sanka MCP Server. Nothing to install.
prepare_buy_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 prepare_buy_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 prepare_buy_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.
prepare_buy_checkout is provided by the Sanka MCP Server MCP server (sankahq/sanka-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 →