AI agents call menami_consult_agent 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 queries and returns personalized recommendations based on user taste profile and preferences. It is purely informational with no side effects, reversible actions, code execution, data destruction, or financial commitments. The read operation has minimal blast radius even if an AI agent misuses it—it simply returns suggestions that the user may ignore.
From the tool's definition Tool description states 'Get personalized restaurant recommendations' — a retrieval operation with no data modification. No booking, ordering, or deletion capabilities mentioned.
Attacks that exploit this kind of access
Get personalized restaurant recommendations from your Menami food agent. 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_consult_agent: 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_consult_agent 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_consult_agent 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_consult_agent. 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_consult_agent 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 →