AI agents call next_steps_dashboard 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.
The tool appears to present information (dashboard) rather than modify, delete, or execute external operations. It reads or displays internal state. The sparse description and '[Interno]' (internal) marking suggest this is an informational/monitoring tool. Without evidence of side effects, it defaults to Read category with low-medium severity due to uncertainty.
From the tool's definition Tool name 'next_steps_dashboard' and description '[Interno] Use' suggest a display or query operation for viewing dashboard data or next steps information. The description is minimal and uninformative, which lowers confidence.
Attacks that exploit this kind of access
[Interno] Use. 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 next_steps_dashboard: 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.
next_steps_dashboard 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 next_steps_dashboard 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 next_steps_dashboard. 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.
next_steps_dashboard 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 →