mcp_kulinar_recommendMeals
Подбирает недельное меню русской кухни с учётом аллергий, нелюбимых ингредиентов и количества едоков. Возвращает план на будни/выходные и список покупок.
This record as markdown: /tools/cowork-bench/mcp-kulinar-recommendmeals.md
What mcp_kulinar_recommendMeals does on Cowork Bench
AI agents call mcp_kulinar_recommendMeals 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_recommendMeals is rated Low
This is a recommendation/query tool that retrieves or generates meal suggestions and shopping lists. It has no side effects on any system, does not create or modify persistent data, does not execute code or commands, and does not involve financial transactions. The most severe category applicable is Read.
From the tool's definition Tool name and description indicate it recommends weekly Russian cuisine menus based on allergies, disliked ingredients, and number of diners.
Attacks that exploit this kind of access
The rule that runs mcp_kulinar_recommendMeals 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_recommendMeals, this is the rule to start with:
mcp_kulinar_recommendMeals 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_recommendMeals call is checked against it from then on.
Questions about mcp_kulinar_recommendMeals
Подбирает недельное меню русской кухни с учётом аллергий, нелюбимых ингредиентов и количества едоков. Возвращает план на будни/выходные и список покупок. 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_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 Cowork Bench. Nothing to install.
mcp_kulinar_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_kulinar_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_kulinar_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_kulinar_recommendMeals 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