AI agents call discover_codebase to retrieve information from Maestro without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves and queries information about the codebase structure, architecture, and technology stack. It has no side effects—it merely inspects and reports findings. This is a classic Read operation (retrieve/query data). Severity is low because misuse would at worst expose information about the codebase architecture, which is informational rather than operationally damaging.
From the tool's definition Tool name 'discover_codebase' combined with description 'Analisa codebase e detecta arquitetura/stack' indicates analysis and detection of existing code structure.
Attacks that exploit this kind of access
Analisa codebase e detecta arquitetura/stack. It is categorised as a Read tool in the Maestro MCP Server, which means it retrieves data without modifying state.
Register the Maestro MCP server in PolicyLayer and add a rule for discover_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.
discover_codebase is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the discover_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 discover_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.
discover_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 →