fulcra-context

Review·Scanned 2/17/2026

Provides agent access to a human's biometrics, sleep, activity, location, and calendar via the Fulcra Life API. The skill stores OAuth tokens at ~/.config/fulcra/token.json, uses FULCRA_ACCESS_TOKEN, and instructs running python3 scripts/fulcra_auth.py and curl against https://api.fulcradynamics.com.

from clawhub.ai·ve2b043d·26.8 KB·0 installs
Scanned from 1.2.0 at e2b043d · Transparency log ↗
$ vett add clawhub.ai/arc-claw-bot/fulcra-contextReview findings below

Fulcra Context — Personal Data for AI Agents

Give your AI agent situational awareness. With your consent, access your biometrics, sleep, activity, location, and calendar data from the Fulcra Life API.

What Is This?

An OpenClaw skill that connects AI agents to the Fulcra personal data platform. Your agent can:

  • Know how you slept → adjust morning briefing tone and intensity
  • See heart rate / HRV trends → detect stress, suggest breaks
  • Check your location → context-aware suggestions (home vs. office vs. traveling)
  • Read your calendar → proactive meeting prep, schedule awareness
  • Track workouts → recovery-aware task scheduling

Why Fulcra?

Most AI agents meet their user for the first time — every time. They have no memory of your health, no awareness of your schedule, no sense of how you're actually doing.

Fulcra fixes that. It aggregates data from Apple Health, wearables, calendars, and manual annotations into a single, normalized API. Your agent gets clean, consistent data regardless of what devices you use.

Privacy-First by Design

  • OAuth2 per-user — you control exactly what your agent sees
  • Consent is revocable — disconnect anytime
  • No data monetization — Fulcra is a paid service, not an ad platform. Your data is never sold.
  • Encryption at rest — GDPR/CCPA compliant

This matters. When you give an AI agent access to your heart rate, sleep patterns, and calendar, you need to trust the platform holding that data. Fulcra's business model is structurally aligned with your privacy — they make money by serving you, not by selling your information.

Quick Start

Option 1: MCP Server (Any AI client)

{
  "mcpServers": {
    "fulcra_context": {
      "command": "npx",
      "args": ["-y", "mcp-remote", "https://mcp.fulcradynamics.com/mcp"]
    }
  }
}

Works with Claude Desktop, Goose, Windsurf, VS Code, and more.

Option 2: OpenClaw Skill

clawdhub install fulcra-context

Or manually: copy SKILL.md to your OpenClaw workspace's skills/fulcra-context/ directory.

Option 3: Direct API

pip install fulcra-api
from fulcra_api.core import FulcraAPI
api = FulcraAPI()
api.authorize()  # Opens browser for OAuth2 consent

# Get last night's sleep
import datetime
end = datetime.datetime.now(datetime.timezone.utc)
start = end - datetime.timedelta(hours=24)
sleep = api.time_series_grouped(
    start_time=start, end_time=end,
    metrics=["SleepStage"], sample_rate=300
)

Available Data

Data TypeExamplesUse Cases
SleepStages (REM, Deep, Light), duration, qualityMorning briefings, energy-aware scheduling
Heart RateBPM, resting rate, trendsStress detection, workout recovery
HRVHeart rate variabilityAutonomic nervous system state, recovery
ActivitySteps, calories, exercise timeActivity-aware recommendations
CalendarEvents, times, locationsProactive scheduling, meeting prep
LocationGPS coordinates, visitsContext-aware suggestions, travel detection
WorkoutsType, duration, intensityRecovery scheduling
CustomManual annotations, moods, symptomsPersonalized context

Integration Patterns

🌅 Context-Aware Morning Briefing

Check sleep quality + today's calendar + weather → compose a briefing calibrated to actual energy level. Poor sleep? Lighter tone, fewer tasks. Great sleep? Full agenda.

💆 Stress-Aware Communication

Monitor HRV + heart rate → if stress indicators are elevated, keep messages brief and avoid adding non-urgent tasks.

🏃 Recovery-Aware Scheduling

After intense workout or poor sleep → suggest lighter schedule, remind about hydration, reschedule demanding work.

✈️ Travel Awareness

Detect location changes → adjust timezone handling, suggest local info, modify schedule expectations.

Security

Read SECURITY.md before deploying. This skill accesses sensitive personal data. Key risks include token exposure, calendar/location leakage, and prompt injection attacks. The security guide covers mitigations for each.

Files

FilePurpose
SKILL.mdOpenClaw skill definition (API reference, quick commands)
SECURITY.mdSecurity & privacy guide (risks, mitigations, best practices)
README.mdThis file

Links

License

MIT