Return the optimal carbon-aware execution window for a task WITHOUT scheduling it. Use this for non-committal planning — when you want to see *when* the cleanest grid moment falls inside the deadline (and what the savings vs running now would be) before deciding whether to commit via schedule_tas...
AI agents call recommend_window to retrieve information from Ebb Ai without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool purely queries and returns informational recommendations about optimal execution windows. It explicitly states it does not schedule or commit to anything, making it a read-only advisory tool with no side effects.
From the tool's definition 'WITHOUT scheduling it', 'non-committal planning', 'want to see *when* the cleanest grid moment falls', 'Returns the chosen window, top 3 alternatives, batch_eligible flag, and a one-line reasoning string'
Attacks that exploit this kind of access
Return the optimal carbon-aware execution window for a task WITHOUT scheduling it. Use this for non-committal planning — when you want to see *when* the cleanest grid moment falls inside the deadline (and what the savings vs running now would be) before deciding whether to commit via schedule_task. Returns the chosen window, top 3 alternatives, batch_eligible flag, and a one-line reasoning string. It is categorised as a Read tool in the Ebb Ai MCP Server, which means it retrieves data without modifying state.
Register the Ebb Ai MCP server in PolicyLayer and add a rule for recommend_window: 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 Ebb Ai. Nothing to install.
recommend_window 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 recommend_window 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 recommend_window. 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.
recommend_window is provided by the Ebb Ai MCP server (vitalini/ebb-ai). 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 →