AI agents call menami_get_restaurant to retrieve information from Menami 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 with no side effects. It does not modify data, execute commands, delete resources, or involve financial transactions. The incomplete description ('including menu' without further details) does not suggest any capability beyond data retrieval. This is a straightforward Read operation with minimal risk.
From the tool's definition Tool name 'menami_get_restaurant' and description 'Get detailed information about a specific restaurant including menu' indicate retrieval of data without modification.
Attacks that exploit this kind of access
Get detailed information about a specific restaurant including menu,. It is categorised as a Read tool in the Menami MCP Server, which means it retrieves data without modifying state.
Register the Menami MCP server in PolicyLayer and add a rule for menami_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 Menami. Nothing to install.
menami_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 menami_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 menami_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.
menami_get_restaurant is provided by the Menami MCP server (menami-ai/menami). 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 →