不知道吃什么？根据人数直接推荐适合的菜品组合
AI agents call mcp_howtocook_whatToEat to retrieve information from HowToCook-MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool performs a read-only query against the recipe database to suggest suitable dish combinations. It has no side effects—it does not create, modify, delete, or execute operations. The only output is informational recommendations. Even if an AI agent misuses it by requesting inappropriate recommendations, the blast radius is minimal since no data is changed and no external systems are affected.
From the tool's definition Tool name 'whatToEat' and description indicate it recommends meal combinations based on number of people. The verb 'recommend' and the context of querying a recipe database show this retrieves and suggests data without modifying, deleting, or executing…
Attacks that exploit this kind of access
不知道吃什么？根据人数直接推荐适合的菜品组合. It is categorised as a Read tool in the HowToCook-MCP Server MCP Server, which means it retrieves data without modifying state.
Register the HowToCook-MCP Server MCP server in PolicyLayer and add a rule for mcp_howtocook_whatToEat: 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 HowToCook-MCP Server. Nothing to install.
mcp_howtocook_whatToEat 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 mcp_howtocook_whatToEat 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 mcp_howtocook_whatToEat. 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.
mcp_howtocook_whatToEat is provided by the HowToCook-MCP Server MCP server (kureha4/mcptest1). 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 →