Remove an item from the cart
AI agents use remove_from_basket to create or update resources in Food402 — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Food402 environment.
Removing an item from a shopping cart modifies the cart state, but is reversible (the item can be re-added). This is a Write operation. It does not finalize a financial transaction, delete persistent data irreversibly, or execute code. Severity is medium because misuse could disrupt a user's order in progress.
From the tool's definition Remove an item from the cart
Documented attack patterns abuse exactly the kind of access remove_from_basket gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Food402, and nothing reaches the server without passing your rules. This is the rule we recommend for remove_from_basket:
{
"version": "1",
"default": "deny",
"tools": {
"remove_from_basket": {
"limits": [
{
"counter": "remove_from_basket_rate",
"window": "minute",
"max": 30,
"scope": "grant"
}
]
}
}
}remove_from_basket stays usable, but capped — an agent stuck in a loop can't make hundreds of changes a minute. Everything else on the server is denied unless you say otherwise.
Free to start. No card required.
Remove an item from the cart. It is categorised as a Write tool in the Food402 MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Food402 MCP server in PolicyLayer and add a rule for remove_from_basket: 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 Food402. Nothing to install.
remove_from_basket 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 remove_from_basket 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 remove_from_basket. 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.
remove_from_basket is provided by the Food402 MCP server (rersozlu/food402). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Food402, 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.
22 Food402 tools catalogued and risk-classified — across an index of 43,000+ MCP servers.