Search for recipes by keyword (example chicken, pepper, steak etc) across the top 900 rated or more recipes
AI agents call search-top-recipes to retrieve information from Mcp Cookbook without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool queries recipe data based on keyword input and returns results. It has no side effects—it does not create, modify, delete, or execute code. The operation is read-only and the blast radius of misuse is minimal (e.g., unexpected search results or information disclosure of public recipes).
From the tool's definition Tool name 'search-top-recipes' and description 'Search for recipes by keyword' indicates a retrieval operation with no modifications. The description explicitly states it searches across existing recipes without creating, modifying, or deleting data.
Attacks that exploit this kind of access
Search for recipes by keyword (example chicken, pepper, steak etc) across the top 900 rated or more recipes. It is categorised as a Read tool in the Mcp Cookbook MCP Server, which means it retrieves data without modifying state.
Register the Mcp Cookbook MCP server in PolicyLayer and add a rule for search-top-recipes: 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 Mcp Cookbook. Nothing to install.
search-top-recipes 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 search-top-recipes 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 search-top-recipes. 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.
search-top-recipes is provided by the Mcp Cookbook MCP server (springdo/mcp-cookbook). 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 →