Opens the browser at the checkout page so you can select a delivery time and pay.
AI agents use finish_session to commit financial operations through Frisco MCP — usually the final step of a payment, billing, or trading workflow. A call moves real money.
This tool initiates the checkout/payment flow by navigating to the payment page, directly enabling financial transactions (purchasing groceries). While it may require manual user confirmation to complete payment, it places the user in the payment flow, making it Financial in category. Misuse could lead to unintended purchases, hence critical severity.
From the tool's definition Opens the browser at the checkout page so you can select a delivery time and pay
Documented attack patterns abuse exactly the kind of access finish_session gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Frisco MCP, and nothing reaches the server without passing your rules. This is the rule we recommend for finish_session:
{
"version": "1",
"default": "deny",
"tools": {
"finish_session": {
"deny_if": [
{
"conditions": [],
"on_deny": "Requires human approval."
}
]
}
}
} Any call to finish_session is blocked until a human approves it. The rest of the server keeps working.
Free to start. No card required.
Opens the browser at the checkout page so you can select a delivery time and pay. It is categorised as a Financial tool in the Frisco MCP MCP Server, which means it involves financial transactions. Block by default and require explicit approval.
Register the Frisco MCP server in PolicyLayer and add a rule for finish_session: 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 Frisco MCP. Nothing to install.
finish_session 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 finish_session 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 finish_session. 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.
finish_session is provided by the Frisco MCP server (mkidawa/frisco-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Frisco MCP, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.
Free to start. No card required.
15 Frisco MCP tools catalogued and risk-classified — across an index of 43,000+ MCP servers.