Rate a recipe 1-5. Call when user says 'that was a 4/5' or similar.
AI agents use rate_recipe to create or update resources in CoupleHub MCP Server — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your CoupleHub MCP Server environment.
The tool creates or updates a rating value associated with a recipe, which is a write operation that modifies data. It is reversible (ratings can be changed), so it does not qualify as Destructive. It has minimal blast radius—the worst case is incorrect recipe ratings, which are non-critical metadata in a recipe management system.
From the tool's definition Tool description states 'Rate a recipe 1-5', which modifies the rating attribute of a recipe record. This is a reversible data modification operation typical of write operations.
Attacks that exploit this kind of access
Rate a recipe 1-5. Call when user says 'that was a 4/5' or similar. It is categorised as a Write tool in the CoupleHub MCP Server MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the CoupleHub MCP Server MCP server in PolicyLayer and add a rule for rate_recipe: 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.
rate_recipe is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the rate_recipe 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 rate_recipe. 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.
rate_recipe 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 →