Urgent.News

One page, thousands of outlets. See who else covered it.

Editions

AI

One MCP server, eight AI clients: Apple Health setup that works everywhere

Most Apple Health MCP guides are per-client. Claude today, Cursor tomorrow, ChatGPT next week. That's the wrong abstraction. MCP is a protocol. The server command is identical across every client. Only the config file path and JSON shape change. What the server exposes Eight read-only tools, all local: Tool What it returns get_mcp_status Health check: data source, metric count, most recent data…

Apple Health's MCP server supports multiple AI clients with a single server setup. The server provides eight read-only tools that return health data in various formats. These tools include: getting the server status, listing all available metrics, retrieving health metrics within a date range, comparing recent data against past data, exporting structured JSON data, getting intraday data, and querying health data using natural language queries.

The server can provide information such as HRV trends, sleep patterns over time, and how resting heart rate changes based on sleep duration. It operates locally on the user's iPhone, delivering live data without the need for CSV files, copy-pasting, or screenshots. The server configuration remains consistent across all AI clients, with only the file path changing.

Written by urgent.news from Dev.to's reporting — not their text. Machine-written — may contain errors; check the original before relying on it.

Read the original at dev.to →

More in AI

Kimi K2 API Integration: A No-Fluff Getting Started

Kimi K2 API Integration: A No-Fluff Getting Started Kimi K2 is Moonshot AI's flagship Mixture-of-Experts model, and the first thing developers notice is what it can see.

  • Kimi K2 integrates images with text in same chat interface.
  • Use API key with cURL or Python SDK for integration.
  • Stream responses by setting stream parameter to True.

How to avoid Claude watermarking your content

The answer is where you least expect it.

  • Anthropic will watermark Claude's LLM output to comply with EU AI Act.
  • Watermarks attach to text based on specific word choices.
  • Researchers seek alternative methods to avoid watermarks.

More from Tuesday 18 August →