Given the ingredients you have on hand, find every cocktail you can make completely — one where you already have all of its ingredients. Garnishes are treated as optional and plain water is assumed available; soda and tonic water are not. Matching is word-based, not substring: "gin" matches "Lond...
Part of the Cocktail Glass server.
Free to start. No card required.
AI agents call find_makeable_cocktails 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 find_makeable_cocktails 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": {
"find_makeable_cocktails": {}
}
}See the full Cocktail Glass policy for all 6 tools.
These attack patterns abuse exactly the kind of access find_makeable_cocktails 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.
Given the ingredients you have on hand, find every cocktail you can make completely — one where you already have all of its ingredients. Garnishes are treated as optional and plain water is assumed available; soda and tonic water are not. Matching is word-based, not substring: "gin" matches "London dry gin" but not "ginger beer", and generic terms do not match product-class extras ("gin" will not cover "sloe gin" or "orange bitters"). Returns two lists: "makeable" (drinks you can make now, up to 60) and "almostMakeable" (drinks exactly one ingredient short, up to 25, each naming the missing ingredient). Drinks needing two or more extra ingredients are omitted entirely. Both lists are ordered simplest first — fewest distinct ingredients in the full recipe, then alphabetical by name. Use this for multi-ingredient "what can I make?" questions; for a single ingredient use find_cocktails_by_ingredient.. 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 find_makeable_cocktails: 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.
find_makeable_cocktails 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 find_makeable_cocktails 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 find_makeable_cocktails. 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.
find_makeable_cocktails 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.