MEAL PLANNING STEP 2. Call once with no filters to get all recipes,
AI agents call get_recipes to retrieve information from CoupleHub 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 recipe data for meal planning purposes. It performs a query operation that returns information without creating, modifying, deleting, or executing any actions. The low severity reflects minimal risk—unauthorized access to recipe data poses negligible harm to the couple or system.
From the tool's definition Tool description states 'get all recipes' with 'no filters', indicating data retrieval without modification. The verb 'get' and action of retrieving recipes are characteristic of read operations.
Attacks that exploit this kind of access
MEAL PLANNING STEP 2. Call once with no filters to get all recipes,. It is categorised as a Read tool in the CoupleHub MCP Server MCP Server, which means it retrieves data without modifying state.
Register the CoupleHub MCP Server MCP server in PolicyLayer and add a rule for get_recipes: 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 CoupleHub MCP Server. Nothing to install.
get_recipes 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_recipes 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_recipes. 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_recipes is provided by the CoupleHub MCP Server MCP server (uczesieweba/couplehub-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 →