BP

bckenstler/py-huckleberry-mcp

开发工具

本页由 AI 翻译,技术细节请以原文为准。 查看原文

4 stars 8 forks 质量 69 趋势 12MIT

Model Context Protocol (MCP) server for Huckleberry baby tracking API

概览

: This is an unofficial, community-built project. It is not sponsored, endorsed, or supported by Huckleberry. Use at your own risk. A Model Context Protocol (MCP) server built with FastMCP that interfaces with the Huckleberry baby tracking API, enabling Claude to help you track your baby's sleep, feeding, diaper changes, and growth measurements through natural conversation. - : List and manage multiple child profiles - : Start, pause, resume, complete, and cancel sleep sessions with automatic history tracking - : Track breastfeeding sessions with side switching - : Record diaper changes with type, amount, color, and consistency details - : Log and retrieve weight, height, and head circumference measurements - Python 3.10 or higher - A Huckleberry account with valid credentials - Claude Desktop application (for integration) - uv package manager (recommended) or pip This server uses the FastMCP framework for rapid MCP server development.

README

以下为原文 README 节选,完整内容请查看原文。

Huckleberry MCP Server

Disclaimer: This is an unofficial, community-built project. It is not sponsored, endorsed, or supported by Huckleberry. Use at your own risk.

A Model Context Protocol (MCP) server built with FastMCP that interfaces with the Huckleberry baby tracking API, enabling Claude to help you track your baby’s sleep, feeding, diaper changes, and growth measurements through natural conversation.

Features

  • Child Management: List and manage multiple child profiles
  • Sleep Tracking: Start, pause, resume, complete, and cancel sleep sessions with automatic history tracking
  • Feeding Tracking: Track breastfeeding sessions with side switching
  • Diaper Logging: Record diaper changes with type, amount, color, and consistency details
  • Growth Tracking: Log and retrieve weight, height, and head circumference measurements

Prerequisites

  • Python 3.10 or higher
  • A Huckleberry account with valid credentials
  • Claude Desktop application (for integration)
  • uv package manager (recommended) or pip

Installation

# Clone or navigate to the project directory
cd /path/to/huckleberry-mcp
uv sync

Using pip

cd /path/to/huckleberry-mcp
pip install -e .

Architecture

This server uses the FastMCP framework for rapid MCP server development. FastMCP provides:

  • Automatic tool registration via decorators
  • Schema generation from type hints and docstrings
  • Built-in error handling and protocol compliance
  • Support for multiple transport types (STDIO, HTTP)

The server implements 22 tools across 5 categories:

  • Child Management (2 tools)
  • Sleep Tracking (7 tools)
  • Feeding Tracking (8 tools)
  • Diaper Tracking (2 tools)
  • Growth Tracking (3 tools)

All tools use lazy authentication - credentials are validated on first tool use rather than at server startup.

Authentication Setup

The server requires your Huckleberry credentials to be configured as environment variables.

Add the server to your Claude Desktop configuration file with your credentials:

macOS: ~/Library/Application Support/Claude/claude_desktop_config.json Windows: %APPDATA%\Claude\claude_desktop_config.json Linux: ~/.config/Claude/claude_desktop_config.json

{
  "mcpServers": {
    "huckleberry": {
      "command": "uv",
      "args": [
        "--directory",
        "/absolute/path/to/huckleberry-mcp",
        "run",
        "huckleberry-mcp"
      ],
      "env": {
        "HUCKLEBERRY_EMAIL": "[email protected]",
        "HUCKLEBERRY_PASSWORD": "your-password",
        "HUCKLEBERRY_TIMEZONE": "America/New_York"
      }
    }
  }
}

Important:

  • Replace /absolute/path/to/huckleberry-mcp with the actual absolute path to this project
  • On macOS, if using Anaconda, specify the full path to uv: /Users/your-username/anaconda3/bin/uv
在 GitHub 查看完整 README

安装

This server does not publish a one-line install command.

Open the repository installation guide 新手?先看 mcpskill.org 教程 →

配置

{ "mcpServers": { "huckleberry": { "command": "uv", "args": [ "--directory", "/absolute/path/to/huckleberry-mcp", "run", "huckleberry-mcp" ], "env": { "HUCKLEBERRY_EMAIL": "[email protected]", "HUCKLEBERRY_PASSWORD": "your-password", "HUCKLEBERRY_TIMEZONE": "America/New_York" } } } }