根据用户的忌口、过敏原、人数智能推荐菜谱，创建一周的膳食计划以及大致的购物清单
AI agents call mcp_howtocook_recommendMeals 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 retrieves and generates meal plan recommendations based on user input parameters (dietary restrictions, allergens, number of people). It produces read-only outputs (recipe suggestions, meal plans, shopping lists) without creating, modifying, executing code, deleting, or transferring financial data. The worst case of misuse would be providing irrelevant meal recommendations, which poses minimal risk.
From the tool's definition The tool 'mcp_howtocook_recommendMeals' provides recipe recommendations and creates meal planning outputs ('根据用户的忌口、过敏原、人数智能推荐菜谱，创建一周的膳食计划以及大致的购物清单' - recommend recipes based on dietary restrictions/allergens/number of people, create a weekly meal plan and…
Documented attack patterns abuse exactly the kind of access mcp_howtocook_recommendMeals gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and HowToCook-MCP Server, and nothing reaches the server without passing your rules. This is the rule we recommend for mcp_howtocook_recommendMeals:
{
"version": "1",
"default": "deny",
"tools": {
"mcp_howtocook_recommendMeals": {}
}
}mcp_howtocook_recommendMeals is read-only, so it stays allowed — but everything else on the server is denied unless you say otherwise.
Free to start. No card required.
根据用户的忌口、过敏原、人数智能推荐菜谱，创建一周的膳食计划以及大致的购物清单. 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_recommendMeals: 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_recommendMeals 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_recommendMeals 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_recommendMeals. 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_recommendMeals is provided by the HowToCook-MCP Server MCP server (worryzyy/howtocook-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Deterministic rules across all 5 HowToCook-MCP Server tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.
Free to start. No card required.
5 HowToCook-MCP Server tools catalogued and risk-classified — across an index of 42,500+ MCP servers.