AI agents call uber_cancel_ride to permanently remove resources in MCP Uber Server — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
While cancellation is technically a state change, it is functionally irreversible and destructive to the ride transaction. Once cancelled, the ride cannot be resumed; a new request must be made. This qualifies as Destructive rather than Write because the action cannot be rolled back and has binding consequences. Severity is high because misuse could cancel legitimate rides, strand users, and incur unexpected fees.
From the tool's definition The tool 'uber_cancel_ride' with description 'Cancel an ongoing ride request' irreversibly terminates an active ride arrangement.
Documented attack patterns abuse exactly the kind of access uber_cancel_ride gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and MCP Uber Server, and nothing reaches the server without passing your rules. This is the rule we recommend for uber_cancel_ride:
{
"version": "1",
"default": "deny",
"hide": [
"uber_cancel_ride"
]
}uber_cancel_ride disappears from the agent's tool list entirely, and any attempt to call it is denied. The rest of the server keeps working.
Free to start. No card required.
Cancel an ongoing ride request. It is categorised as a Destructive tool in the MCP Uber Server MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the MCP Uber Server MCP server in PolicyLayer and add a rule for uber_cancel_ride: 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 MCP Uber Server. Nothing to install.
uber_cancel_ride is a Destructive 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 uber_cancel_ride 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 uber_cancel_ride. 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.
uber_cancel_ride is provided by the MCP Uber Server MCP server (199-mcp/mcp-uber). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from MCP Uber Server, 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.
6 MCP Uber Server tools catalogued and risk-classified — across an index of 43,000+ MCP servers.