AI agents call get_ride_options to retrieve information from Mcp Lyft without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool queries and returns data about available ride types without any side effects, state changes, or financial obligations. It is purely informational—similar to a search or list operation. The user must subsequently call request_ride to actually book and incur financial responsibility. This is a classic Read operation with minimal risk.
From the tool's definition The tool description states 'Get available Lyft ride types' with no mention of creation, modification, deletion, or financial commitment. It retrieves information about available ride options for display purposes.
Attacks that exploit this kind of access
Get available Lyft ride types (Lyft, Lyft XL, Lux, Lux Black, etc.) for the current route. It is categorised as a Read tool in the Mcp Lyft MCP Server, which means it retrieves data without modifying state.
Register the Mcp Lyft MCP server in PolicyLayer and add a rule for get_ride_options: 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.
get_ride_options is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the get_ride_options 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 get_ride_options. 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.
get_ride_options 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 →