AI agents call search_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 and queries recipe data without modifying, deleting, or executing any operations. It returns metadata about recipes (name, status, version, identifiers) with no side effects. This is a straightforward read operation with minimal risk if misused by an AI agent.
From the tool's definition Tool name 'search_recipe' and description 'Busca fichas tecnicas pelo nome e retorna status, versao atual e identificadores' (searches technical sheets by name and returns status, current version and identifiers) indicate query and retrieval operations only.
Attacks that exploit this kind of access
Busca fichas tecnicas pelo nome e retorna status, versao atual e identificadores. 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 search_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.
search_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 search_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 search_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.
search_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 →