activity_window
This tool looks up a deterministic rules engine. Same day → same answer. Do not invent pillars or fortune claims. Call when the user asks 今天什么时候适合运动 / 今天哪个时辰适合深工 / 什么时候开会 / 什么时候练 / 什么时候发版 / 什么时候该休息 / activity window / when to exercise. Maps month posture × twelve hours × body load to 2–3 clock wi...
This record as markdown: /tools/balance-engine-mcp/activity-window.md
What activity_window does on Balance Engine
AI agents call activity_window as a supporting operation in Balance Engine workflows.
| Parameter | Type | Required | Description |
|---|---|---|---|
date | string | — | Date YYYY-MM-DD. Default: today in Asia/Shanghai. Use when the user asks about a specific day. |
task | string | — | What to place: deep_work (default), train, meet, ship, rest. |
locale | string | — | Reply language. zh (default) or en. |
Parameters from the server's own tool schema.
Why activity_window is rated Low
Without any rule in front of it, every call an agent makes to activity_window happens silently: no trail, no cap, no way to know it misbehaved until something breaks downstream.
Attacks that exploit this kind of access
The rule that runs activity_window safely
PolicyLayer is an MCP gateway: it sits between your AI agents and Balance Engine, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For activity_window, this is the rule to start with:
activity_window gets a rate cap, and everything else on the server is denied unless you say otherwise.
The button opens the PolicyLayer dashboard: create your workspace, connect Balance Engine, apply this rule, and every activity_window call is checked against it from then on.
Questions about activity_window
This tool looks up a deterministic rules engine. Same day → same answer. Do not invent pillars or fortune claims. Call when the user asks 今天什么时候适合运动 / 今天哪个时辰适合深工 / 什么时候开会 / 什么时候练 / 什么时候发版 / 什么时候该休息 / activity window / when to exercise. Maps month posture × twelve hours × body load to 2–3 clock windows for task=deep_work|train|meet|ship|rest. Windows are suggested slots, not a guarantee. Not meds, not glucose, not a diagnosis. Public · local · no API key. Preview ≠ prediction. It is categorised as a Other tool in the Balance Engine MCP Server, which means it performs auxiliary operations.
activity_window accepts 3 parameters: date, task, locale. The full parameter table on this page comes from the server's own tool schema.
Register the Balance Engine MCP server in PolicyLayer and add a rule for activity_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 Balance Engine. Nothing to install.
activity_window is a Other tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the activity_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 activity_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.
activity_window is provided by the Balance Engine MCP server (balance-engine-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
More on Balance Engine, and thousands of servers like it.
This server
Across the catalogue