Skip to main content

​
Integration Options

Arlo Health provides three integration methods:

MCP (Recommended)

Model Context Protocol for native AI agent integration. Tools are discovered automatically.

OpenClaw Plugin

One-command install for OpenClaw agents. Wraps the REST API with OpenClaw-compatible tooling.

REST API

Traditional REST endpoints for direct HTTP integration.

​
Core Workflow

Every Arlo consultation follows this flow:
1

Gather Context

Have a natural conversation with the user to understand their health concern
2

Start Consultation

Call start_healthcare_consultation with a first-person narrative
3

AI Triage

Respond to AI follow-up questions using send_message
4

Payment Gate

Handle payment confirmation based on user’s billing mode
5

Provider Match

User is matched with a licensed nurse practitioner
6

Active Consultation

User exchanges messages with provider asynchronously
7

Closed

Consultation completes with clinical notes and optional prescription

​
Step 1: Gather Context

Before starting a consultation, have a natural conversation with the user to understand their health concern:
  • What’s the main symptom?
  • How long has it been going on?
  • Any associated symptoms?
  • Has this happened before?

​
Step 2: Start Consultation

Call start_healthcare_consultation with a first-person narrative: 
{
  "contextMessage": "I've had a sore throat for 3 days. It started with a scratchy feeling and now it hurts to swallow. I don't have a fever but I've been feeling tired. I had strep throat last year with similar symptoms."
}
Rich, narrative context helps the AI triage system gather information faster, reducing the number of follow-up questions.

​
Step 3: Respond to AI Triage

The AI triage system will ask follow-up questions. Use send_message to respond with natural, detailed answers: 
{
  "conversationId": "abc123",
  "messages": ["No fever, but I've been feeling really tired and run down the past few days."]
}

​
Step 4: Handle Payment Gate

After triage completes, the consultation enters PAYMENT_REQUIRED status. Check the paymentType:
  • pay_per_use: Call confirm_provider_connection to place a $30 hold and proceed
  • subscription_required: Guide user through subscription setup flow

​
Step 5: Provider Consultation

Once a provider is matched, the consultation becomes ACTIVE. The user can exchange messages with the provider asynchronously. Providers can:
  • Ask additional questions
  • Provide diagnosis and treatment recommendations
  • Write prescriptions (sent to selected pharmacy)

​
Authentication

For new users, call init_signup to start the OAuth flow:
  1. Call init_signup — returns an authUrl
  2. User opens the URL and completes signup
  3. Poll check_account_status until authenticated: true
See Authentication for the full OAuth 2.1 flow and discovery endpoints. Without webhooks, your agent must poll for updates. With webhooks, Arlo pushes notifications when:
  • Provider sends a message
  • AI triage responds
  • Consultation status changes
  • Provider connects or consultation closes
{
  "webhookUrl": "https://your-agent/hooks/arlo",
  "webhookToken": "your-secret-token",
  "deliveryContext": {
    "to": "+15551234567",
    "channel": "whatsapp",
    "deliver": true
  }
}
See Webhooks for full documentation.

​
Next Steps

MCP Tools Overview

Explore all available MCP tools

Consultation Lifecycle

Understand consultation status flow

Authentication

Deep dive into OAuth 2.1 setup

Payment Options

Learn about billing modes