Get all cocktails you can make with ingredients on your bar shelf
AI agents call get_shelf_cocktails to retrieve information from Bar Assistant MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This is a read-only query operation that retrieves cocktail information without creating, modifying, deleting, or executing external operations. It has minimal blast radius - an AI agent cannot cause harm by retrieving cocktail recommendations. The data returned is informational only.
From the tool's definition Tool description states 'Get all cocktails you can make' - a retrieval operation with no modification or deletion of data. The name 'get_shelf_cocktails' and description indicate querying existing cocktail data based on available ingredients.
Attacks that exploit this kind of access
Get all cocktails you can make with ingredients on your bar shelf. It is categorised as a Read tool in the Bar Assistant MCP Server MCP Server, which means it retrieves data without modifying state.
Register the Bar Assistant MCP Server MCP server in PolicyLayer and add a rule for get_shelf_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 Bar Assistant MCP Server. Nothing to install.
get_shelf_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 get_shelf_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 get_shelf_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.
get_shelf_cocktails is provided by the Bar Assistant MCP Server MCP server (the-real-py/bar-assistant-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 →