Suggest one cocktail picked uniformly at random from the catalogue (or from one family if "family" is given) and return its full recipe — ingredients with measures, preparation steps, garnish, glassware, page URL, and any film or TV appearances. Each call returns an independent draw, so repeated ...
Part of the Cocktail Glass server.
Free to start. No card required.
AI agents call random_cocktail to retrieve information from Cocktail Glass without modifying any data. This is common in research, monitoring, and reporting workflows where the agent needs context before taking action. Because read operations don't change state, they are generally safe to allow without restrictions -- but you may still want rate limits to control API costs.
Even though random_cocktail only reads data, uncontrolled read access can leak sensitive information or rack up API costs. An agent caught in a retry loop could make thousands of calls per minute. A rate limit gives you a safety net without blocking legitimate use.
Read-only tools are safe to allow by default. No rate limit needed unless you want to control costs.
{
"version": "1",
"default": "deny",
"tools": {
"random_cocktail": {}
}
}See the full Cocktail Glass policy for all 6 tools.
These attack patterns abuse exactly the kind of access random_cocktail gives an agent. Each links to the full case and the policy that stops it:
Other read tools across the catalogue. The same approach applies to each: allow, with a rate cap to control cost.
Suggest one cocktail picked uniformly at random from the catalogue (or from one family if "family" is given) and return its full recipe — ingredients with measures, preparation steps, garnish, glassware, page URL, and any film or TV appearances. Each call returns an independent draw, so repeated calls give different drinks. The "family" filter matches the family name exactly (case- and diacritic-insensitive); if no cocktail matches that family the call silently falls back to the full catalogue rather than erroring. Use this only when the user wants a suggestion or inspiration with no specific drink in mind. For a named cocktail use get_cocktail_recipe; for "anything with gin" use find_cocktails_by_ingredient; for "what can I make from what I have" use find_makeable_cocktails.. It is categorised as a Read tool in the Cocktail Glass MCP Server, which means it retrieves data without modifying state.
Register the Cocktail Glass MCP server in PolicyLayer and add a rule for 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 Glass. Nothing to install.
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 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 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.
random_cocktail is provided by the Cocktail Glass MCP server (https://cocktail.glass/mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Deterministic rules across all 6 Cocktail Glass tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.
Free to start. No card required.
4,600+ MCP servers and 31,000+ tools scanned and risk-classified.