Get today's menu from Tekuila restaurant.
AI agents call get_current_day_menu to retrieve information from Tekuila MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves restaurant menu data without modifying, executing, or deleting any information. It is a straightforward data retrieval operation that presents minimal security risk—the worst case being exposure of publicly available menu information.
From the tool's definition Tool name 'get_current_day_menu' and description 'Get today's menu from Tekuila restaurant' indicate a retrieval operation with no side effects. The verb 'Get' and the server context of 'retrieve daily or weekly menus' confirm this is a read-only query.
Attacks that exploit this kind of access
Get today's menu from Tekuila restaurant. It is categorised as a Read tool in the Tekuila MCP Server MCP Server, which means it retrieves data without modifying state.
Register the Tekuila MCP Server MCP server in PolicyLayer and add a rule for get_current_day_menu: 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 Tekuila MCP Server. Nothing to install.
get_current_day_menu 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_current_day_menu 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_current_day_menu. 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_current_day_menu is provided by the Tekuila MCP Server MCP server (mtpajula/tekuila-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 →