AI agents use atualizar_codebase 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.
The tool updates codebase information, which is a write operation. Marked as [Interno] (Internal), suggesting it modifies internal state or metadata about the codebase. The description is minimal, reducing confidence. Since it updates rather than deletes, Write is the appropriate category, though if it overwrites code files it could be more severe.
From the tool's definition 'Atualiza informações do codebase' — 'Atualiza' means 'Updates' in Portuguese, indicating a write/modification operation on the codebase information.
Attacks that exploit this kind of access
[Interno] Atualiza informações do codebase. 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.
Register the Maestro MCP server in PolicyLayer and add a rule for atualizar_codebase: 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.
atualizar_codebase 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 atualizar_codebase 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 atualizar_codebase. 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.
atualizar_codebase 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.
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 →