confirmar_classificacao · Maestro MCP: Risk & Policy

WHAT IT DOES

What confirmar_classificacao does on Maestro

AI agents use confirmar_classificacao to create or update resources in Maestro — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Maestro environment.

WHY IT NEEDS A POLICY

Why confirmar_classificacao needs a policy

The tool appears to confirm/commit a reclassification decision following a PRD review, which is a write/state-change operation. It modifies some classification state within the system. Confidence is moderate because the description is very brief and internal ('[Interno]'), leaving the exact scope and blast radius unclear. Reclassification is likely reversible, placing it in Write rather than Destructive.

From the tool's definition 'Confirma reclassificação após PRD' — confirms a reclassification after a PRD (Product Requirements Document)

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

confirmar_classificacao Rate-limited

confirmar_classificacao stays usable, but capped — an agent stuck in a loop can't make hundreds of changes a minute. Everything else on the server is denied unless you say otherwise.

View as policy code

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "confirmar_classificacao": {
      "limits": [
        {
          "counter": "confirmar_classificacao_rate",
          "window": "minute",
          "max": 30,
          "scope": "grant"
        }
      ]
    }
  }
}

LIMIT THIS TOOL →

Instant setup, no code required.

PolicyLayer is an MCP gateway: every tool call is checked against your rule before it reaches Maestro, so you can run agents against it safely.

FAQ

Questions about confirmar_classificacao

What does the confirmar_classificacao tool do? +

[Interno] Confirma reclassificação após PRD. It is categorised as a Write tool in the Maestro MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.

How do I enforce a policy on confirmar_classificacao? +

Register the Maestro MCP server in PolicyLayer and add a rule for confirmar_classificacao: 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 Maestro. Nothing to install.

What risk level is confirmar_classificacao? +

confirmar_classificacao is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.

Can I rate-limit confirmar_classificacao? +

Yes. Add a rate_limit block to the confirmar_classificacao 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.

How do I block confirmar_classificacao completely? +

Set action: deny in the PolicyLayer policy for confirmar_classificacao. 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.

What MCP server provides confirmar_classificacao? +

confirmar_classificacao is provided by the Maestro MCP server (matheus-gama-deluna/maestro). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.