How to Create a Daily Productivity Report with GitHub Copilot

What You Are Making

A GitHub Copilot Agent prompt that reads yesterday's screen time data from ScreenTimerAI and generates a short daily productivity report inside VS Code.

No extra tools. No browser. Just Copilot and your data.

Why GitHub Copilot

GitHub Copilot is GitHub's AI coding assistant built directly into VS Code. It offers chat, code completions, and Agent mode — a powerful capability that lets Copilot call external tools on your behalf. Millions of developers already rely on Copilot for code suggestions every day. Connecting screen time tracking to Copilot makes sense because it is already part of your daily workflow. Adding time tracking data through MCP means you can get productivity insights without leaving the tool you already use for coding. Agent mode handles MCP tool calls seamlessly, so asking Copilot about your screen time feels just like asking it about your code.

Step 1: Connect ScreenTimerAI To GitHub Copilot

There are two ways to set this up:

.vscode/mcp.json

{
  "servers": {
    "screentimerai-activities": {
      "type": "stdio",
      "command": "/Applications/ScreenTimerAI.app/Contents/MacOS/activity-mcp-server",
      "args": []
    }
  }
}

If you want to test that Step 1 worked, switch to Agent mode and try one of these prompts:

Step 2: Generate Your Daily Report

Open Copilot Chat (Cmd+Shift+I) and switch to Agent mode using the mode selector at the top. Then paste this prompt:

Generate a daily productivity text report based on yesterday's Screen Time AI data.

Follow these steps:

1. Fetch yesterday's activity data from Screen Time AI.
2. Write a short productivity report (~150 words) from the perspective of a dark, witty productivity coach reacting to the data.

Rules:
- Focus more on failures than successes
- Use short, punchy sentences
- Be dark and witty, commanding not polished
- Swearing is allowed sparingly for impact
- Return only the final report text, nothing else

Return the report as plain text directly in the chat.

Copilot will discover the ScreenTimerAI tools automatically and ask for approval before executing. Approve the calls and the report appears in the chat.

Other Prompts To Try

Once the MCP connection is working, you are not limited to the daily report prompt above. Here are a few more prompts you can paste into Copilot Agent mode to explore your screen time data in different ways:

• "Show me my top 5 apps by time spent yesterday." Get a quick ranked breakdown of where your hours actually went so you can spot time sinks at a glance.
• "How many context switches did I have yesterday afternoon?" Find out how often you jumped between apps during a specific window. Frequent switches usually signal interruption-heavy stretches.
• "Compare my screen time this week vs last week." See whether your overall usage is trending up or down and which apps are driving the change.
• "Analyze my focus segments for yesterday and identify my most productive hours." Let Copilot pinpoint the time blocks where you stayed locked in so you can protect those slots going forward.

Troubleshooting

• MCP tools not showing? You must be in Agent mode in Copilot Chat. The "Ask" and "Edit" modes do not have access to MCP tools. Use the mode selector at the top of the chat panel to switch.
• Server not connecting? MCP support in Copilot requires VS Code 1.99 or later. Make sure the setting chat.mcp.enabled is set to true in your VS Code settings (Cmd+Shift+P, then "Preferences: Open Settings (JSON)").
• Tools not discovered? Click the tools icon (wrench) in the Copilot Chat panel to see the list of available MCP tools. If ScreenTimerAI tools are listed but greyed out, toggle them on from that menu.

What Happens Next

Every time you run the prompt in Agent mode, GitHub Copilot pulls your latest screen time data through the MCP connection and generates a fresh report.

Keep it as a pinned prompt for a quick morning check-in inside VS Code.