Search dishes across all restaurants. Pick the best match for user.
AI agents call search_menu_items to retrieve information from MCP A2A AP2 Food Delivery & Payments without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool searches and queries menu data without creating orders, modifying data, or triggering payments. It is purely informational and returns results to help the user choose items. The action is read-only with no destructive, financial, or executable consequences.
From the tool's definition Tool name 'search_menu_items' and description 'Search dishes across all restaurants. Pick the best match for user.' indicate a retrieval/query operation with no side effects.
Attacks that exploit this kind of access
Search dishes across all restaurants. Pick the best match for user. It is categorised as a Read tool in the MCP A2A AP2 Food Delivery & Payments MCP Server, which means it retrieves data without modifying state.
Register the MCP A2A AP2 Food Delivery & Payments MCP server in PolicyLayer and add a rule for search_menu_items: 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 A2A AP2 Food Delivery & Payments. Nothing to install.
search_menu_items 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_menu_items 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_menu_items. 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_menu_items is provided by the MCP A2A AP2 Food Delivery & Payments MCP server (tas1337/mcp-a2a-ap2-im-hungry). 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 →