Skip to main content
Glama
RescueTime MCP Server

RescueTime MCP Server

RescueTime MCP Server

A lightweight MCP server that gives Claude access to your RescueTime productivity data. Built with FastMCP.

Tools

Tool

Description

get_daily_summary

Productivity pulse, hours logged, productive vs. distracting time breakdown

get_top_activities

Top apps/websites ranked by time spent

get_categories

Time breakdown by category (Development, Communication, Social, etc.)

get_productivity_trend

Productivity pulse trend over the past N days

All tools accept a day parameter: "today", "yesterday", or "YYYY-MM-DD".

Related MCP server: RescueTime MCP Server

Install

Open Claude Code, paste:

/plugin marketplace add adelaidasofia/rescuetime-mcp
/plugin install rescuetime-mcp@rescuetime-mcp

Then get a RescueTime API key at rescuetime.com/anapi/manage and set RESCUETIME_API_KEY in your environment.

1. Get your API key

Go to rescuetime.com/anapi/manage and create or copy an API key.

2. Download the server and install it

You need git and uv. If you don't have Python 3.11 or newer, uv downloads it for you.

git clone https://github.com/adelaidasofia/rescuetime-mcp.git "$HOME/rescuetime-mcp"
uv sync --directory "$HOME/rescuetime-mcp"

uv sync installs everything the server needs (FastMCP, httpx and mycelium-security, a URL safety check) at the versions pinned in uv.lock.

3. Add to Claude Code

claude mcp add rescuetime -s user \
  -e RESCUETIME_API_KEY=your_api_key_here \
  -- uv run --directory "$HOME/rescuetime-mcp" fastmcp run server.py

This works in every project. Or, for one project only, add this to that project's .mcp.json (Claude Code asks you to approve it the first time you start there), replacing /path/to/rescuetime-mcp with the full path of the folder from step 2:

{
  "mcpServers": {
    "rescuetime": {
      "command": "uv",
      "args": ["run", "--directory", "/path/to/rescuetime-mcp", "fastmcp", "run", "server.py"],
      "env": {
        "RESCUETIME_API_KEY": "your_api_key_here"
      }
    }
  }
}

4. Restart Claude Code

The RescueTime tools should appear in your session. Start Claude Code from your own project, not from inside the rescuetime-mcp folder: that folder has its own .mcp.json for the plugin, which clashes with this server.

Example Usage

Once connected, you can ask Claude things like:

  • "How productive was I today?"

  • "What apps did I spend the most time on yesterday?"

  • "Show me my productivity trend for the last 7 days"

  • "What categories did I spend time on this week?"

Requirements

  • Python 3.11+

  • FastMCP 3.x

  • A RescueTime account (free or premium)

  • RescueTime API key

How It Works

The server calls the RescueTime Analytic Data API using your API key and returns structured productivity data that Claude can reason about. No data is stored or sent anywhere except back to your Claude session.

Same author, same architecture pattern (FastMCP, draft+confirm on writes where applicable, vault auto-export, MIT):

Telemetry

This plugin sends a single anonymous install signal to myceliumai.co the first time it loads in a Claude Code session on a given machine.

What is sent:

  • Plugin name (e.g. slack-mcp)

  • Plugin version (e.g. 0.1.0)

What is NOT sent:

  • No user identifiers, names, emails, tokens, or API keys

  • No file paths, message content, or anything from your work

  • No IP address is stored after dedup processing

Why: Helps the maintainer know which plugins people actually install, so attention goes to the ones that get used.

Opt out: Set the environment variable MYCELIUM_NO_PING=1 before launching Claude Code. The hook will skip the network call entirely. Already-pinged installs leave a sentinel at ~/.mycelium/onboarded-<plugin> — delete it if you want to reset state.

License

MIT


Built by Mycelium AI. Full install or team version at diazroa.com.

Available Tools

5 tools
get_activity_dataA

Get top activities/applications by time spent.

Args: date_str: Date to query - 'today', 'yesterday', or 'YYYY-MM-DD' limit: Maximum number of activities to show (default: 10)

Shows which specific applications and websites you spent time on, ranked by duration. Includes productivity classification for each.

Inputs: date_str, limit. Returns: result

get_category_breakdownA

Get time spent by category.

Args: date_str: Date to query - 'today', 'yesterday', or 'YYYY-MM-DD'

Shows high-level categories like Software Development, Communication, Reference & Learning, etc. with time and productivity classification.

Inputs: date_str. Returns: result

get_hourly_productivityA

Get productivity breakdown by hour.

Args: date_str: Date to query - 'today', 'yesterday', or 'YYYY-MM-DD'

Shows when during the day you were most/least productive. Useful for identifying peak productivity hours and scheduling deep work.

Inputs: date_str. Returns: result

get_productivity_trendB

Get productivity pulse trend for the last N days.

Args: days: Number of days to look back (default: 7, max 14)

Shows the daily productivity pulse with visual bars and calculates averages. Useful for identifying patterns and trends over time.

Inputs: days. Returns: result

get_today_summaryA

Get today's complete RescueTime productivity summary.

This is the recommended daily check-in tool. Returns:

  • Productivity pulse (0-100 score)

  • Total time logged

  • Time breakdown by productivity level

  • Productive vs distracting percentages

Inputs: no named parameters. Returns: result

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

Loading tool schema changelog…

    TDQS

    A4/5.0

    Scored across 5 tools

    Disambiguation5/5

    Each tool has a clearly distinct focus: activity details, category aggregation, hourly productivity, trend over days, and a comprehensive daily summary. No overlap between tools.

    Naming Consistency5/5

    All tools follow a consistent 'get_<descriptive_noun>' pattern with snake_case, making it predictable for an agent to infer function from name.

    Tool Count5/5

    Five tools is well-scoped for a personal productivity monitoring server, covering key aspects without unnecessary complexity or missing essentials.

    Completeness4/5

    The tool set covers daily summary, detailed activities, categories, hourly breakdown, and trends. Minor gaps like historical data export or multi-day comparison are acceptable.

    Maintenance

    ActivityActive
    ResponsivenessNo recent community issues

    Related MCP Connectors

    Related MCP Servers

    • A
      license
      Not graded
      quality
      D
      maintenance
      Enables comprehensive access to RescueTime productivity data and features through the Model Context Protocol. Supports analytics retrieval, focus session management, highlights creation, and offline time tracking through natural language interactions.
      12
      MIT
    • A
      license
      Not graded
      quality
      D
      maintenance
      Connects your Whoop health data to Claude, enabling natural language queries about recovery, sleep, strain, and workouts.
      MIT