Vaultbeat MCP Server

Your AI agent reads your E2EE Apple Health data (sleep, HRV, cycle) — decrypted only locally

Local serverstdioPython

What is the Vaultbeat MCP server?

If you already use Vaultbeat, the vaultbeat mcp server is the piece that lets your assistant work with it directly. Your AI agent reads your E2EE Apple Health data (sleep, HRV, cycle) — decrypted only locally.

What the server does

Vaultbeat embeds no AI and runs no model on your phone. Intelligence lives where you control it: Claude Code, Claude Desktop, or any MCP-capable agent running on your own machine. This server is the bridge — it holds a private key that never leaves your computer, pulls ciphertext from the cloud, and decrypts only locally.

Available tools

The toolset is worth reading before you wire it up, because it tells you what the integration is really for:

  • vaultbeat_status — Local binding state (never exposes keys or tokens)
  • vaultbeat_doctor — Full self-diagnosis: install/binding chain plus which data types have data and which need a newer iOS build — call this before concluding data is
  • vaultbeat_start_binding — A fresh QR binding payload for the iOS app to scan
  • vaultbeat_poll_binding — One poll for the iOS authorization to complete binding
  • vaultbeat_sync_sleep — Recent sleep sessions incl. heart-rate samples, per-day primary-session selection matching the iOS app
  • get_sleep_detail — Per-night heart-rate + respiratory-rate + sleep-stage timeline
  • get_water_intake — Daily water intake + computed daily average
  • get_weight_trend — Daily weights + latest/avg/min/max + weekly trend rate
  • get_menstrual_cycle — Cycle samples + next-period prediction (sensitive — explicit iOS opt-in required)
  • get_symptoms — HealthKit symptom days grouped by data owner (sensitive)
  • get_notes — Free-text day annotations with their writer (sensitive)
  • get_activity — Daily activity rings: steps / energy / exercise minutes / stand hours / distance

Installation

Installation goes through your MCP client rather than a global install: point it at @modelcontextprotocol/inspector on npm and it is fetched when the client starts. The copy-paste blocks for Claude Desktop, Claude Code and Cursor are further down this page.

Credentials and setup notes

  • Vaultbeat — AI Health Sync on iOS, with a Pro subscription (the AI-agent interface is the Pro tier) - Python 3.11+ on the machine where your agent runs (macOS / Linux / Windows)

Where it fits

Among the developer tooling options, the useful question is rarely "what can it do" but "what does it cost you to run" — permissions, credentials, and how much of your context its toolset consumes. Vaultbeat's toolset — vaultbeat_status, vaultbeat_doctor, vaultbeat_start_binding and 11 more — is a fair guide to whether it matches your workflow. It is maintained by Fino-wind; worth a glance at recent repository activity before you build anything load-bearing on it.

SyncDev reviews every entry in this directory against the project's own documentation before publishing, and revisits them as servers change.

Worth knowing first

  • It runs with your machine's permissions. That is convenient and also the reason to think about what you point it at before you approve a tool call.
  • With 14 tools registered it takes up a noticeable share of the context window; turn it off in projects that never touch Vaultbeat.
  • Keep per-call confirmation enabled while you learn its behaviour; it is the cheapest safeguard you have.

Available tools

ToolWhat it does
vaultbeat_statusLocal binding state (never exposes keys or tokens)
vaultbeat_doctorFull self-diagnosis: install/binding chain **plus** which data types have data and which need a newer iOS build — call this before concluding data is missing
vaultbeat_start_bindingA fresh QR binding payload for the iOS app to scan
vaultbeat_poll_bindingOne poll for the iOS authorization to complete binding
vaultbeat_sync_sleepRecent sleep sessions incl. heart-rate samples, per-day primary-session selection matching the iOS app
get_sleep_detailPer-night heart-rate + respiratory-rate + sleep-stage timeline
get_water_intakeDaily water intake + computed daily average
get_weight_trendDaily weights + latest/avg/min/max + weekly trend rate
get_menstrual_cycleCycle samples + next-period prediction *(sensitive — explicit iOS opt-in required)*
get_symptomsHealthKit symptom days grouped by data owner *(sensitive)*
get_notesFree-text day annotations with their writer *(sensitive)*
get_activityDaily activity rings: steps / energy / exercise minutes / stand hours / distance
get_resting_hrResting heart-rate records + window mean
get_workoutsWorkout records: type / duration / calories / distance

How to install the Vaultbeat MCP server

{
  "mcpServers": {
    "vaultbeat": {
      "command": "npx",
      "args": ["-y", "@modelcontextprotocol/inspector"]
    }
  }
}

Add to claude_desktop_config.json, then restart Claude Desktop.

Configuration

  • Vaultbeat — AI Health Sync on iOS, with a Pro subscription (the AI-agent interface is the Pro tier) - Python 3.11+ on the machine where your agent runs (macOS / Linux / Windows)

Example prompts to try

  • Use Vaultbeat to vaultbeat status.
  • Use Vaultbeat to vaultbeat doctor.
  • Use Vaultbeat to vaultbeat start binding.

Frequently asked questions

It connects Vaultbeat to MCP-compatible AI assistants such as Claude and Cursor, exposing 14 tools (vaultbeat_status, vaultbeat_doctor, vaultbeat_start_binding, and more) that the assistant can call on your behalf. Instead of copying data back and forth by hand, the assistant works with Vaultbeat directly.