Wellness Planner

Provides an MCP server that queries simulated health data and schedules tasks using energy-aware planning.

python

0

GitHub Stars

python

Language

4 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": {
    "rwking-wellness_planner": {
      "command": "uv",
      "args": [
        "run",
        "--directory",
        "/path/to/wellness_planner",
        "python",
        "mcp_server/server.py"
      ]
    }
  }
}

You run a local MCP server named Wellness Planner MCP Server that coordinates with a client to query simulated personal health data and schedule tasks in an energy-aware way. This setup lets you explore how the agent and MCP server collaborate to retrieve health insights and propose efficient daily plans.

How to use

You connect to the Wellness Planner MCP Server from an MCP client (Cursor or a compatible tool). Once connected, you can discover the health data schema, run analyses on stored health data, generate charts, and ask the agent to propose an energy-aware daily schedule based on your tasks and readiness scores. The server uses simulated data seeded into a local SQLite database and returns actionable outputs such as summaries, readiness, and suggested scheduling.

How to install

Prerequisites: Python 3.14 or newer and a local MCP client capable of connecting via stdio.

Install the local Wellness Planner MCP components and prepare the environment.

Run the Cursor-configured MCP server as described below to enable the Cursor connection.

{
  "mcpServers": {
    "wellness-planner": {
      "type": "stdio",
      "command": "uv",
      "args": ["run", "--directory", "/path/to/wellness_planner", "python", "mcp_server/server.py"]
    }
  }
}

Additional notes

The MCP server path is designed for integration with Cursor. The server process is started by Cursor when needed, using the stdio channel to communicate. If you are working locally without Cursor, you can run the server directly with the same Python entry point that Cursor would invoke.

Available tools

get_health_summary

Fetches aggregated health metrics such as sleep, activity, and heart rate for a given date.

calculate_readiness_score

Computes a 1–10 readiness score to guide task timing based on health signals.

query_raw_logs

Runs read-only SQL queries against the health database to inspect data.

get_tasks

Loads tasks from the local to-do list file.

propose_schedule

Generates an energy-aware daily schedule based on readiness and available tasks.

get_data_dictionary

Inspects the health data schema to reveal tables, columns, and sample values.

run_analysis

Executes analysis scripts locally using pandas and SQLite to derive insights.

generate_chart

Creates a self-contained chart visualization from health data.

get_insights

Retrieves previously saved findings from the fact store.

save_insight

Saves a discovered insight to avoid recomputation in future sessions.