AI agents use create_new_version to create or update resources in Fichapao — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Fichapao environment.
This tool creates new data (a draft recipe version) and modifies the recipe sheet's version history, which is a Write operation. It is reversible (versions can be archived or updated). Severity is medium because creating incorrect recipe drafts in a bakery system could lead to production issues if approved, but the draft status means it's not immediately destructive.
From the tool's definition Tool description states 'Cria uma nova versao em rascunho' (creates a new draft version), which is a create/modify operation.
Attacks that exploit this kind of access
Cria uma nova versao em rascunho a partir da versao atual da ficha. It is categorised as a Write tool in the Fichapao MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Fichapao MCP server in PolicyLayer and add a rule for create_new_version: 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.
create_new_version 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 create_new_version 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 create_new_version. 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.
create_new_version 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 →