Search for meals and dishes in the SommelierX database. Returns meal names, IDs, and descriptions. Use this to discover available meals before using pair_wine_with_meal or group_pairing. Best for:
AI agents call search_meals to retrieve information from SommelierX Wine Pairing MCP without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This is a straightforward query/search tool that retrieves data from the SommelierX database without side effects. It discovers available meals to inform downstream pairing recommendations but does not create, modify, delete, or execute any operations. The blast radius of misuse is minimal — an attacker gains only read access to the meal database.
From the tool's definition Tool description explicitly states it "Search for meals and dishes" and "Returns meal names, IDs, and descriptions" — purely informational retrieval with no modification, deletion, or execution of external operations.
Attacks that exploit this kind of access
Search for meals and dishes in the SommelierX database. Returns meal names, IDs, and descriptions. Use this to discover available meals before using pair_wine_with_meal or group_pairing. Best for:. It is categorised as a Read tool in the SommelierX Wine Pairing MCP MCP Server, which means it retrieves data without modifying state.
Register the SommelierX Wine Pairing MCP server in PolicyLayer and add a rule for search_meals: 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 SommelierX Wine Pairing MCP. Nothing to install.
search_meals 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 search_meals 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 search_meals. 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.
search_meals is provided by the SommelierX Wine Pairing MCP server (rogertheunissenmerge-oss/mcp-server). 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 →