AI agents use approve_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.
approve_version modifies existing recipe version records by changing their approval status and potentially promoting version numbers. This is a Write operation rather than Execute because it updates structured data with deterministic effects (approval state transition), not arbitrary code execution. It's not Destructive because the change is reversible and doesn't delete data.
From the tool's definition Tool description states 'Aprova uma versao' (approves a version) and 'Versoes 0.x viram 1.0' (versions 0.x become 1.0), indicating state modification of recipe versions in the database.
Attacks that exploit this kind of access
Aprova uma versao se nao houver pendencias criticas. Versoes 0.x viram 1.0 na primeira aprovacao. 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 approve_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.
approve_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 approve_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 approve_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.
approve_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 →