Huckleberry Mcp

What is Huckleberry Mcp?

Huckleberry Mcp is an unofficial MCP (Model Context Protocol) server that integrates with the Huckleberry baby tracker. It allows AI assistants like Claude Desktop, Cursor, and VS Code to query and log baby sleep, feeds, diapers, pumping, solids, potty, and growth records.

How to use Huckleberry Mcp?

Install globally via npm install -g node-huckleberry-mcp or run directly with npx node-huckleberry-mcp. Configure credentials through environment variables (HUCKLEBERRY_EMAIL, HUCKLEBERRY_PASSWORD, HUCKLEBERRY_TIMEZONE) or a .env file. For Claude Desktop, add the server entry to claude_desktop_config.json with the command and environment variables.

Key features of Huckleberry Mcp

• Query and log sleep, feeding, and diaper records
• Manage growth measurements and solids/custom foods
• 24 MCP tools across 6 categories
• Supports nursing, bottle, solids, and pumping
• Edit existing entries via edit_* tools
• MCP prompts for daily summaries and event logging

Use cases of Huckleberry Mcp

• Ask an AI assistant for the latest sleep or feeding history of your child
• Log a diaper change or nursing session with specific details via natural language
• Retrieve growth measurements and compare trends over time
• Manage custom foods and list curated food databases
• Integrate baby tracking data into automated routines or daily reports

FAQ from Huckleberry Mcp

What tools does Huckleberry Mcp expose?

It exposes 24 tools across child management, sleep, feeding, diaper, growth, and solids‑custom foods categories. See the full table in the README.

What are the runtime requirements?

Node.js 18+ and npm 9+ are required. The server is tested on Node 24.

How do I configure Huckleberry Mcp?

Set environment variables HUCKLEBERRY_EMAIL, HUCKLEBERRY_PASSWORD, and HUCKLEBERRY_TIMEZONE. You can also copy .env.example to .env and edit it.

Can I write data to Huckleberry?

Yes, the log_* tools (e.g., log_sleep, log_bottle, log_diaper) insert new records. Active‑session timers (like start_sleep) are not implemented; only completed events can be logged.

Is this an official Huckleberry product?

No, it is an unofficial MCP server. It is a Node.js port of two MIT‑licensed projects (py-huckleberry-api and py-huckleberry-mcp).