AI agents call get_recipe to retrieve information from Fichapao without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves bakery recipe technical sheets based on provided identifiers or names. It performs a lookup/query operation without modifying, deleting, or executing any data. The verb 'consulta' (consults/queries) and the read-only nature of parameter-based retrieval classify this as a Read operation with low severity—an AI agent cannot cause harm by retrieving recipe information.
From the tool's definition Tool name 'get_recipe' and description 'Consulta uma ficha tecnica por recipe_id, version_id ou nome' (Consults/queries a technical sheet by recipe_id, version_id or name) indicate a read-only query operation with no side effects.
Attacks that exploit this kind of access
Consulta uma ficha tecnica por recipe_id, version_id ou nome. It is categorised as a Read tool in the Fichapao MCP Server, which means it retrieves data without modifying state.
Register the Fichapao MCP server in PolicyLayer and add a rule for get_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 Fichapao. Nothing to install.
get_recipe 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_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 get_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.
get_recipe is provided by the Fichapao MCP server (kratos4ai/fichapao-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 →