Tracker

Exposes task logging, updating, and time-based summaries through MCP for local productivity tracking.

python

1

GitHub Stars

python

Language

5 months ago

First Indexed

2 months ago

Catalog Refreshed

Documentation & install

Readme and setup notes from the catalogue, plus a client-ready config you can copy for your MCP host.

Installation

Add the following to your MCP client configuration file.

Configuration

View docs

{
  "mcpServers": {
    "manasamadgul-tracker": {
      "command": "C:\\path\\to\\python.exe",
      "args": [
        "C:\\path\\to\\ProductivityTracker\\mcp_server.py"
      ]
    }
  }
}

You can interact with your tasks through an MCP server that exposes productivity tools for logging, updating, removing, and summarizing tasks via a standard protocol. This server runs locally, leverages a language model interface for natural conversations, and integrates with Claude Desktop for a seamless, conversational MCP experience.

How to use

Set up the MCP server and connect using an MCP client to manage tasks with natural language queries. You can log tasks, view time-based summaries, update or remove tasks by ID or name, and get quick insights like daily, weekly, or monthly summaries. Use natural phrases to perform actions, for example: log a task, show today’s summary, update a task status, or delete a task.

How to install

Prerequisites: ensure you have Python 3.12 or newer installed on your system and Ollama with the llama3.2 model ready. If you want Claude Desktop MCP integration, have Claude Desktop installed as well.

Install and set up the Productivity Tracker locally by following these steps.

# Step 1: Clone the project repository
git clone cd ProductivityTracker

# Step 2: Install Python dependencies
pip install -r requirements.txt

# Step 3: Install Ollama and pull the llama3.2 model
ollama pull llama3.2

# Step 4: Initialize the database
python -c "import database; database.init_db()"

Additional setup for MCP server usage

If you plan to use Claude Desktop as your MCP client, configure Claude Desktop to point to the local MCP server by editing the provided configuration snippet. Then restart Claude Desktop to establish the MCP connection.

Starting the local agent or MCP server

Option 1: Run the local LangChain agent to test queries directly against the local model and tools.

Option 2: Use the MCP server with Claude Desktop to interact through natural language. The MCP server runs as a stdio process and is invoked by Claude Desktop.

Available tools

log_task

Create or log a new task with a category and initial status, including optional details like name, description, and due date.

get_summary

Retrieve time-based summaries (daily, weekly, monthly) for a given period, aggregating task counts and statuses.