Search for recipes by keyword across categories
AI agents call search_recipes_by_category 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 performs a search operation that queries the recipe database and returns results. It has no side effects—it does not create, modify, delete, or execute any operations. The action is purely retrieving information based on search criteria, which is characteristic of a Read category tool.
From the tool's definition "Search for recipes by keyword across categories" - the tool searches and retrieves recipe data without modifying, deleting, or executing external operations.
Attacks that exploit this kind of access
Search for recipes by keyword across categories. 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_recipes_by_category: 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_recipes_by_category 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_recipes_by_category 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_recipes_by_category. 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_recipes_by_category 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 →