AI agents use request_ride to commit financial operations through Mcp Lyft — usually the final step of a payment, billing, or trading workflow. A call moves real money.
Requesting and booking a Lyft ride is a financial transaction that commits the user to a fare payment obligation. When confirm=true, it irreversibly books a ride and triggers a financial charge. Even as a preview, the tool's primary purpose is to initiate a paid ride-sharing transaction, placing it firmly in the Financial category — the most severe applicable.
From the tool's definition Request a Lyft ride... set confirm=true to actually book the ride
Attacks that exploit this kind of access
Request a Lyft ride. Returns a confirmation preview by default — set confirm=true to actually book the ride. It is categorised as a Financial tool in the Mcp Lyft MCP Server, which means it involves financial transactions. Block by default and require explicit approval.
Register the Mcp Lyft MCP server in PolicyLayer and add a rule for request_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 Lyft. Nothing to install.
request_ride 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 request_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 request_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.
request_ride is provided by the Mcp Lyft MCP server (markswendsen-code/mcp-lyft). 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 →