Look up a restaurant by its platform-specific ID. Returns full details including name, address, cuisine, hours, contact info, and booking options.
AI agents call get_restaurant to retrieve information from Restaurant Reservation 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 and queries restaurant information (name, address, cuisine, hours, contact info, booking options) without modifying, deleting, or executing any operations. It is a straightforward data retrieval function with no capability to book, cancel, or alter reservations. The blast radius of misuse is minimal—an attacker could only gather restaurant information, which is typically public data.
From the tool's definition Tool name 'get_restaurant' and description 'Look up a restaurant by its platform-specific ID. Returns full details...' indicates a lookup/retrieval operation with no side effects.
Attacks that exploit this kind of access
Look up a restaurant by its platform-specific ID. Returns full details including name, address, cuisine, hours, contact info, and booking options. It is categorised as a Read tool in the Restaurant Reservation MCP Server MCP Server, which means it retrieves data without modifying state.
Register the Restaurant Reservation MCP Server MCP server in PolicyLayer and add a rule for get_restaurant: 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 Restaurant Reservation MCP Server. Nothing to install.
get_restaurant 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_restaurant 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_restaurant. 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_restaurant is provided by the Restaurant Reservation MCP Server MCP server (jrklein343-svg/restaurant-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 →