AI agents use set_destination to create or update resources in Mcp Lyft — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Mcp Lyft environment.
This tool writes/modifies ride configuration data (the destination). It is reversible in that the destination can be changed before a ride is confirmed. It does not directly move money or execute code, though it is a precursor to requesting a ride. Classified as Write with medium severity since setting a wrong destination could lead to an unintended ride request.
From the tool's definition "Set the destination for your ride" — modifies the destination parameter of a ride request
Attacks that exploit this kind of access
Set the destination for your ride. It is categorised as a Write tool in the Mcp Lyft MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Mcp Lyft MCP server in PolicyLayer and add a rule for set_destination: 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.
set_destination 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 set_destination 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 set_destination. 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.
set_destination 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 →