Search for restaurants and food on DoorDash
AI agents call search_restaurants to retrieve information from DoorDash MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves information about available restaurants and food items. Searching is a read-only operation that does not create, modify, delete, or execute any state-changing actions. The lack of side effects and the explicit 'search' verb clearly indicate Read category. Severity is low because misuse would only expose public restaurant information available to any DoorDash user.
From the tool's definition Tool name is 'search_restaurants' and description states 'Search for restaurants and food on DoorDash' — a query operation with no side effects.
Attacks that exploit this kind of access
Search for restaurants and food on DoorDash. It is categorised as a Read tool in the DoorDash MCP Server MCP Server, which means it retrieves data without modifying state.
Register the DoorDash MCP Server MCP server in PolicyLayer and add a rule for search_restaurants: 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 DoorDash MCP Server. Nothing to install.
search_restaurants 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 search_restaurants 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 search_restaurants. 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.
search_restaurants is provided by the DoorDash MCP Server MCP server (spunkysarb/doordash-mcp). 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 →