AI agents call get_ingredient_info 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 performs a read-only lookup operation to retrieve ingredient information. It has no side effects, does not modify or delete data, does not execute code or scripts, and does not involve financial transactions. The blast radius of misuse is minimal—an AI agent could only retrieve ingredient data, which is public recipe information.
From the tool's definition Tool description states it 'Get[s] detailed information about a cocktail ingredient' with no indication of modification, deletion, or execution of commands. The function retrieves and queries ingredient metadata from TheCocktailDB API.
Attacks that exploit this kind of access
Get detailed information about a cocktail ingredient, including description, type, and whether it contains alcohol. 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 get_ingredient_info: 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.
get_ingredient_info 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 get_ingredient_info 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 get_ingredient_info. 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.
get_ingredient_info 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 →