Arquiva uma ficha tecnica e suas versoes ativas.
AI agents call archive_recipe to permanently remove resources in Fichapao — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
Archiving a recipe and all its active versions is effectively a destructive action — it removes the recipe from active availability. While archiving may not permanently delete data from the database, it renders the recipe and versions inaccessible/inactive in a way that is typically not easily reversible, and affects all associated versions.
From the tool's definition 'Arquiva uma ficha tecnica e suas versoes ativas' — archives a technical sheet and its active versions, an irreversible or difficult-to-reverse operation that removes items from active use
Attacks that exploit this kind of access
Arquiva uma ficha tecnica e suas versoes ativas. It is categorised as a Destructive tool in the Fichapao MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the Fichapao MCP server in PolicyLayer and add a rule for archive_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.
archive_recipe is a Destructive tool with critical risk. Critical-risk tools should be blocked by default and only enabled with explicit human approval.
Yes. Add a rate_limit block to the archive_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 archive_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.
archive_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 →