ActivityWatch MCP Server
Tracks browsing activity and time spent in the Arc browser, enabling AI assistants to categorize usage under browsing and include it in daily activity summaries and timeline views.
Tracks time spent on Bilibili, categorizing the activity as entertainment for daily and weekly usage reports and productivity analysis.
Tracks design activity within Canva, enabling AI assistants to report time spent on design tasks and categorize usage under the design category in activity summaries.
Tracks communication activity in Discord, allowing AI assistants to summarize time spent in communication tools, categorize usage accordingly, and analyze daily patterns.
Tracks time spent working in Figma, categorizing activity under design and enabling project time analysis based on window titles for creative work summaries.
Tracks browsing activity and time spent in Firefox, supporting retrieval of website history (via browser extension) and inclusion in browsing statistics and daily summaries.
Tracks terminal and command-line activity in iTerm2, categorizing usage under coding and enabling project identification from window titles for development time analysis.
Tracks entertainment time spent on Netflix, categorizing the activity for daily and weekly leisure usage summaries and productivity reporting.
Tracks writing and productivity time in Notion, categorizing usage under writing for activity summaries, timeline views, and documentation work analysis.
Tracks note-taking and writing activity in Obsidian, enabling time tracking for knowledge management tasks and categorization under writing activities.
Tracks coding activity in PyCharm, including project identification from window titles and reporting time spent in the IDE for development summaries and coding category analysis.
Tracks browsing activity and time spent in Safari, enabling retrieval of website history and browsing statistics as part of daily activity summaries.
Tracks design activity in Sketch, categorizing time spent under the design category for creative work analysis and productivity reporting.
Tracks communication activity in Slack, enabling summaries of time spent in team communication and collaboration tools as part of daily usage analysis.
Tracks entertainment and media consumption time in Spotify, categorizing usage under entertainment in daily activity reports and usage breakdowns.
Tracks communication activity in Telegram, allowing categorization of time spent in messaging applications within daily and weekly summaries.
Tracks terminal activity in the Warp terminal, categorizing usage under coding and supporting project time tracking based on window titles.
Tracks communication activity in WeChat, enabling tracking of time spent in messaging applications and categorization under communication activities.
Tracks coding and development activity in Xcode, including project identification from window titles for iOS/macOS development time analysis and coding category summaries.
Tracks video consumption time on YouTube, categorizing activity as entertainment in daily usage summaries and productivity analysis.
Tracks communication and meeting time in Zoom, enabling analysis of time spent in video conferencing and categorization under communication activities.
Click on "Install Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@ActivityWatch MCP Serverhow did I spend my time today?"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
An MCP server that gives AI assistants real-time awareness of your computer activity through ActivityWatch. No raw queries. No AQL syntax. Just ask your AI "what did I do today?" and get a human-readable answer.
Why this one?
There are other ActivityWatch MCPs out there. Here's how this one is different:
This project | Others | |
Query interface | Pre-aggregated, high-level tools | Raw AQL queries |
User needs to know AQL? | No | Yes |
Built-in categories | ✅ coding, browsing, communication, etc. | ❌ |
Ready-to-use tools |
|
|
Designed for | AI companions & chat interfaces | Developer debugging |
TL;DR: Other MCPs give your AI a database console. This one gives your AI eyes.
What can your AI do with this?
Once connected, your AI companion can answer questions like:
🕐 "What am I working on right now?"
📊 "How did I spend my time today?"
💻 "How many hours did I code this week?"
🌙 "What time did I stop working last night?"
🔍 "Show me everything I did between 2pm and 5pm yesterday."
🌐 "What websites did I spend the most time on?"
📁 "Which projects did I work on this week?"
🏷️ "Add Cursor to my coding category."
Your AI knows what you do, not just what you say. It can notice patterns you miss — like when you've been coding for 5 hours straight without a break.
Quick Start
1. Prerequisites
ActivityWatch installed and running
Node.js >= 20
2. Install
git clone https://github.com/JM-404/activitywatch-mcp.git
cd activitywatch-mcp
npm install && npm run build3. Configure
Add to your Claude Desktop / Claude Code MCP config:
{
"mcpServers": {
"activitywatch": {
"command": "node",
"args": ["/absolute/path/to/activitywatch-mcp/dist/index.js"]
}
}
}4. Try it
Open Claude and ask: "What have I been doing on my computer today?"
That's it. No AQL. No bucket IDs. Just conversation.
Tools
get_current_activity
"What am I doing right now?"
Returns the currently active app, window title, duration, and AFK status.
get_day_summary
"How did I spend my time today?"
Top apps by usage time, total active/AFK hours, first and last active timestamps.
Parameters: date (optional, defaults to today)
get_category_time
"How many hours did I code this week?"
Aggregated time for a category or specific app over a date range, with daily breakdown.
Parameters: category (required), start_date, end_date (optional)
Built-in categories:
Category | Apps |
| VS Code, PyCharm, Terminal, iTerm2, Cursor, Warp, Xcode |
| Chrome, Safari, Firefox, Arc, Edge |
| WeChat, Slack, Discord, Telegram, Messages, Zoom, Teams |
| Bilibili, YouTube, Spotify, Netflix |
| Obsidian, Notion, Typora, Word, Pages |
| Figma, Sketch, Canva, Photoshop |
Customize categories with AW_CATEGORIES_FILE env var pointing to your own JSON.
get_timeline
"Walk me through my afternoon."
Chronological list of app switches with window titles and durations.
Parameters: date, start_time, end_time, min_duration_seconds
get_browser_history
"What websites did I visit today?"
Top domains by time spent. Requires the ActivityWatch browser extension.
Parameters: date, domain (optional filter)
manage_categories
"Add Cursor to my coding category."
View and modify activity category mappings at runtime. Changes persist to ~/.activitywatch-mcp/categories.json.
Parameters: action (list | add | remove | update), category, apps
get_project_time
"Which projects did I work on this week?"
Coding time broken down by project/repository. Extracts project names from IDE window titles (VS Code, Cursor, PyCharm, Xcode, Terminal).
Parameters: start_date, end_date (optional)
Natural language dates
All date parameters accept natural language in addition to YYYY-MM-DD:
today, yesterday, this_week, last_week, this_month, last_month, last_7_days, last_30_days
Environment Variables
Variable | Default | Description |
|
| ActivityWatch API address |
|
| Truncate window titles for privacy |
| built-in | Path to custom category mapping JSON |
Privacy
🔒 Your data never leaves your machine.
ActivityWatch stores everything locally
This MCP server runs locally
Data flows:
ActivityWatch (local) → MCP Server (local) → Your AI conversationWindow titles are truncated to prevent accidental exposure of sensitive content
No telemetry, no external API calls, no cloud storage
Roadmap
macOS Screen Time integration (iPhone + Mac data from
knowledgeC.db)Auto-generated daily/weekly reports
Proactive alerts (e.g., "You've been coding for 4 hours — take a break")
Productivity scoring and trend analysis
SSE transport for remote access
Contributing
PRs and issues welcome. If you have ideas for new tools or categories, open an issue.
License
MIT
This server cannot be installed
Resources
Unclaimed servers have limited discoverability.
Looking for Admin?
If you are the server author, to access and configure the admin panel.
Latest Blog Posts
MCP directory API
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/JM-404/activitywatch-mcp'
If you have feedback or need assistance with the MCP directory API, please join our Discord server