home / mcp / personal productivity mcp server

Personal Productivity MCP Server

Provides career domain tools for job search, application tracking, and pipeline analysis within Claude.

Installation

Add the following to your MCP client configuration file.

Configuration

{
  "mcpServers": {
    "benro-personal-productivity-mcp": {
      "command": "docker",
      "args": [
        "exec",
        "-i",
        "personal-productivity-mcp",
        "python",
        "-m",
        "mcp_server.server"
      ],
      "env": {
        "LOG_LEVEL": "INFO",
        "DATABASE_PATH": "/path/to/db.sqlite",
        "CACHE_TTL_JOBS": "3600",
        "MCP_SERVER_PORT": "<MCP_SERVER_PORT>",
        "PLAYWRIGHT_HEADLESS": "true"
      }
    }
  }
}

You can run a personal productivity MCP server that provides career-focused tools through Claude, enabling job search automation, application tracking, and pipeline analysis. This server is designed to work locally or in a container and connects to Claude via an MCP client, letting you perform practical, real-time productivity tasks across domains.

How to use

To use the MCP server, connect it to your MCP client or Claude Desktop as shown in the setup steps. Once connected, you can search for jobs using Greenhouse and Lever scrapers, track new applications, update statuses, and view statistics about your application pipeline. You will interact with the system by issuing natural language requests such as searching for software engineering roles or tracking a new application. The server will route your requests to the appropriate tools under the Career domain: read tools for searching, write tools for tracking, and analysis tools for pipeline metrics.

How to install

Prerequisites you need before installing the MCP server are Docker and Docker Compose, and Claude Desktop or a compatible MCP client.

Step by step setup and run process:

# Prerequisites check
docker --version
docker-compose --version

# 1. Clone the project
# (Run in your desired directory)
cd personal-productivity-mcp

# 2. Copy the environment template
cp .env.example .env

# 3. Build and run with Docker
docker-compose up --build

Connecting to Claude Desktop

You connect the MCP server to Claude Desktop by adding a server configuration that runs the MCP server inside Docker or directly with Python. Choose the method that fits your workflow.

Docker method (uses the running container named for the MCP server):

{
  "mcpServers": {
    "personal-productivity": {
      "command": "docker",
      "args": [
        "exec",
        "-i",
        "personal-productivity-mcp",
        "python",
        "-m",
        "mcp_server.server"
      ]
    }
  }
}

Local development without Docker

If you prefer running the MCP server locally without Docker, use Python directly to start the server.

{
  "mcpServers": {
    "personal-productivity": {
      "command": "python",
      "args": ["-m", "mcp_server.server"],
      "cwd": "/path/to/personal-productivity-mcp",
      "env": {
        "PYTHONPATH": "/path/to/personal-productivity-mcp/src"
      }
    }
  }
}

Available tools

career_search_greenhouse

Search jobs on Greenhouse job boards.

career_search_lever

Search jobs on Lever job boards.

career_get_applications

Get tracked applications with optional status filter.

career_track_application

Track a new job application.

career_update_application

Update application status and notes.

career_analyze_pipeline

Get statistics about your application pipeline.