AI agents call search_by_ingredient to retrieve information from Cocktail without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool queries the TheCocktailDB API to retrieve cocktail information based on an ingredient parameter. It performs a read-only search operation that returns filtered results without creating, modifying, deleting, or executing any operations. The data returned (cocktail names and thumbnails) is purely informational with no capability to affect system state or external systems.
From the tool's definition Tool description states it 'Find cocktails that can be made with a specific ingredient. Returns a list of cocktail names and thumbnails.' The verb 'Find' and 'Returns' indicate data retrieval with no modification or side effects.
Attacks that exploit this kind of access
Find cocktails that can be made with a specific ingredient. Returns a list of cocktail names and thumbnails. It is categorised as a Read tool in the Cocktail MCP Server, which means it retrieves data without modifying state.
Register the Cocktail MCP server in PolicyLayer and add a rule for search_by_ingredient: 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 Cocktail. Nothing to install.
search_by_ingredient 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_by_ingredient 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_by_ingredient. 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_by_ingredient is provided by the Cocktail MCP server (yusuke-shibata23/cocktail-mcp). 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 →