mcp_kulinar_whatToEat
Не знаете что приготовить — подскажет набор блюд на застолье по числу гостей (мясное/рыбное горячее + салаты/гарниры).
This record as markdown: /tools/cowork-bench/mcp-kulinar-whattoeat.md
What mcp_kulinar_whatToEat does on Cowork Bench
AI agents call mcp_kulinar_whatToEat to retrieve information from Cowork Bench without modifying anything. It is typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
Why mcp_kulinar_whatToEat is rated Low
This tool queries meal recommendations based on guest count. It retrieves information without creating, modifying, executing code, deleting data, or moving money. The action is purely informational—suggesting menu options. Classification as Read is appropriate for recommendation/lookup tools.
From the tool's definition The tool suggests dishes based on number of guests (provides a set of meat/fish hot dishes + salads/side dishes). The Russian description indicates it 'advises' (подскажет) a menu—a retrieval/query operation with no side effects on data.
Attacks that exploit this kind of access
The rule that runs mcp_kulinar_whatToEat safely
PolicyLayer is an MCP gateway: it sits between your AI agents and Cowork Bench, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For mcp_kulinar_whatToEat, this is the rule to start with:
mcp_kulinar_whatToEat is read-only, so it stays allowed. Everything else on the server is denied unless you say otherwise.
The button opens the PolicyLayer dashboard: create your workspace, connect Cowork Bench, apply this rule, and every mcp_kulinar_whatToEat call is checked against it from then on.
Questions about mcp_kulinar_whatToEat
Не знаете что приготовить — подскажет набор блюд на застолье по числу гостей (мясное/рыбное горячее + салаты/гарниры). It is categorised as a Read tool in the Cowork Bench MCP Server, which means it retrieves data without modifying state.
Register the Cowork Bench MCP server in PolicyLayer and add a rule for mcp_kulinar_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 Cowork Bench. Nothing to install.
mcp_kulinar_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_kulinar_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_kulinar_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_kulinar_whatToEat is provided by the Cowork Bench MCP server (0717376/cowork_bench). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
More on Cowork Bench, and thousands of servers like it.
This server
Across the catalogue