AI agents call get_random_cocktail 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 retrieves and queries data (a random cocktail record) from an external API without any capability to create, modify, delete, or execute operations. It has no financial impact and poses no security risk beyond data exposure. The blast radius of misuse is minimal — an agent could only receive unwanted cocktail suggestions, which is harmless.
From the tool's definition Tool description states 'Get a random cocktail suggestion' and 'discovering new drinks' — pure data retrieval with no modification, deletion, or execution capabilities. Returns recipe information from TheCocktailDB API without side effects.
Attacks that exploit this kind of access
Get a random cocktail suggestion with full recipe details. Great for discovering new drinks. 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_random_cocktail: 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_random_cocktail 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_random_cocktail 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_random_cocktail. 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_random_cocktail 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 →