What You Are Making
A Continue.dev Agent prompt that reads yesterday's screen time data from ScreenTimerAI and generates a short daily productivity report inside VS Code or JetBrains.
No extra apps. No browser. Just your IDE and your data.
Why Continue.dev
Continue.dev is an open-source AI coding assistant that runs as an extension for VS Code and JetBrains. Unlike closed-source alternatives, it is fully customizable and model-agnostic — you can connect it to any LLM provider, from OpenAI and Anthropic to local models running on Ollama. Developers who want full control over their AI tooling without vendor lock-in tend to reach for Continue. Its Agent mode already handles multi-step tasks like reading files, running commands, and chaining tool calls together. Adding screen time tracking data gives the agent context about your actual work patterns so it can reason about productivity, not just code. Since Continue supports the Model Context Protocol natively, connecting ScreenTimerAI is straightforward — just a config entry and you are done.
Step 1: Connect ScreenTimerAI To Continue.dev
Open your Continue config file:
~/.continue/config.yaml
Add ScreenTimerAI under the mcpServers key:
mcpServers:
- name: screentimerai-activities
command: /Applications/ScreenTimerAI.app/Contents/MacOS/activity-mcp-server
args: []
Save and reload Continue.
If you want to test that Step 1 worked, switch to Agent mode and try one of these prompts:
| 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
Open the Continue chat panel and switch to Agent mode. 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.The agent will discover the ScreenTimerAI tools automatically and call them to fetch your data. The report appears in the chat panel.
Other Prompts To Try
Once the MCP connection is working, you are not limited to the daily report prompt above. Continue.dev's Agent mode can call any of the ScreenTimerAI tools on the fly, so you can ask open-ended questions about your screen time data. Here are a few ideas to get you started:
- "Show me my top 5 apps by time spent yesterday." The agent will pull your activity logs and rank applications by total usage, giving you a quick overview of where your hours went.
- "How many context switches did I have yesterday afternoon?" This surfaces how often you bounced between apps during a specific time window — useful for spotting fragmented work sessions.
- "Compare my screen time this week vs last week." The agent fetches data for both ranges and highlights differences, so you can see trends without opening a dashboard.
- "Analyze my focus segments for yesterday and identify my most productive hours." This combines focus-segment analysis with time-of-day breakdown so you know when your deep work actually happens.
Mix and match these with your own questions. The agent figures out which MCP tools to call based on what you ask.
Troubleshooting
If something is not working as expected, check these common issues first:
- Tools not appearing? Make sure you are in Agent mode, not basic chat mode. MCP tools are only available to the agent — the standard chat interface cannot call external tools.
- Config not loading? Verify the YAML syntax is correct. Indentation matters in YAML, so a single misaligned space can break the config. After fixing, reload the Continue extension from the command palette or restart your IDE.
- Server not connecting? Check that the binary path
/Applications/ScreenTimerAI.app/Contents/MacOS/activity-mcp-serverexists and is executable. You can verify by running it directly in your terminal. If it fails, try restarting VS Code or JetBrains to force Continue to re-initialize the MCP connection.
What Happens Next
Every time you run the prompt in Agent mode, Continue.dev pulls your latest screen time data through the MCP connection and generates a fresh report.
Use it as a quick daily check-in right inside your editor.