How to Create a Daily Productivity Report with Claude Code and Time Tracking

Claude Code plus ScreenTimerAI equals a productivity report

What You Are Making

A Claude Code command that pulls yesterday's screen time data from ScreenTimerAI and returns a short daily productivity report in your terminal.

No browser. No GUI. Just a prompt and a result.

Why Claude Code

Claude Code is Anthropic's CLI agent for terminal-based AI coding. It runs directly in your shell, reads and writes files, executes commands, and talks to external services through the Model Context Protocol (MCP). Developers who already live in the terminal — running builds, managing git, tailing logs — can stay there instead of switching to a browser-based chat window.

Connecting screen time tracking to Claude Code makes sense because the workflow never leaves your terminal. You type a prompt, Claude Code calls the ScreenTimerAI MCP server, and the report prints right below. You can pipe the output to a file, feed it into a script, or chain it with other CLI tools. There is no context switch, no extra app to open, and no dashboard to click through. It fits into the same muscle memory you already use for everything else.

Step 1: Connect ScreenTimerAI To Claude Code

There are two ways to add the MCP server:

Run this in your terminal:

claude mcp add screentimerai-activities /Applications/ScreenTimerAI.app/Contents/MacOS/activity-mcp-server

Verify it was added:

claude mcp list

Verify the connection by starting Claude Code and running /mcp to check the server status.

Available ScreenTimerAI Tools

If you want to test that Step 1 worked, try one of these prompts in Claude Code:

MCP function	Test prompt
`get_current_activity`	`What am I doing right now?`
`get_activity_logs`	`Get my raw activity logs for yesterday.`
`show_activity_timeline`	`Show me an activity timeline for yesterday.`
`summarize_activity_range`	`Summarize my activity for yesterday.`
`analyze_focus_segments`	`Analyze my focus segments for yesterday afternoon.`
`show_focus_score_timeline`	`Show me a focus score timeline for today.`
`show_focus_score_trends`	`Show me my focus score last week.`

Step 2: Generate Your Daily Report

Start a Claude Code session and 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.

Claude Code will ask for permission the first time it calls ScreenTimerAI tools. Approve the tool calls and the report appears right in your terminal.

Optional: Automate It

You can run this as a one-liner with claude and pipe the output wherever you want:

claude -p "Fetch yesterday's activity from ScreenTimerAI and write a 150-word productivity report. Be dark and witty."

Combine it with a cron job or a shell alias for a daily check-in that runs without any manual steps.

Other Prompts To Try

The daily report is just one example. Once the MCP connection is live, you can ask Claude Code anything about your screen time data. Here are a few prompts that work well for developers who want quick answers without leaving the terminal:

Top apps by time: "Show my top 5 apps by time spent yesterday." Useful for spotting whether you actually spent the day coding or got pulled into Slack and email.
Context switch count: "How many context switches did I have yesterday afternoon?" High context switching usually means too many meetings or too much multitasking. This prompt quantifies it.
Week-over-week comparison: "Compare my screen time this week vs last week." A quick way to see trends — are you working more, less, or just differently?
Focus segment analysis: "Analyze my focus segments for yesterday and identify my most productive hours." Pinpoints your deep work windows so you can protect them on your calendar.

Each prompt runs as a single command and prints the result directly in your shell. Pipe to pbcopy, redirect to a file, or chain with jq — whatever fits your workflow.

Troubleshooting

If something is not working, check these common Claude Code-specific issues:

Server not showing in /mcp? Make sure the binary path exists and is executable. Run ls -la /Applications/ScreenTimerAI.app/Contents/MacOS/activity-mcp-server to confirm. If the file is missing, reinstall ScreenTimerAI from the website.
Permission denied on tool calls? Claude Code prompts you to approve MCP tool calls the first time. Accept the permission request when it appears. You can also run claude mcp list to verify the server is registered and its current status.
MCP server disconnected? This can happen if ScreenTimerAI was quit or restarted while Claude Code was running. Exit your Claude Code session and start a new one — the MCP connection resets on launch.

What Happens Next

Every time you run the prompt, Claude Code pulls your latest screen time data through the MCP connection and returns a fresh report.

Use it as a morning ritual, pipe it into a log file, or feed it into another tool. The data is yours.