Integration

MCP Integration

Connect AI models to ETERA via Model Context Protocol

Overview

ETERA implements the Model Context Protocol (MCP) across all four verticals, providing a standardized interface for AI models to discover and execute travel operations.

Restaurant MCP

Dining search, reservations, restaurant data

Experience MCP

Activity search, bookings, experience data

Hotel MCP

Hotel search, room booking, property data

Flight MCP

Flight search, pricing, airline data

The Restaurant Booking service also exposes MCP endpoints directly at /restaurant/booking/mcp/*, aggregating booking-specific tools.

Core Endpoints

Every MCP service exposes the same set of endpoints:

MethodEndpointDescription
GET/mcp/toolsList all available tools with schemas
GET/mcp/tools/{tool}Get details for a specific tool
POST/mcp/execute/{tool}Execute a tool with parameters
GET/mcp/servicesList registered backend services
GET/mcp/healthMCP aggregator health status
POST/mcp/refreshRefresh the tool cache

How It Works

1

Discover available tools

List all tools for a vertical to see what operations are available:

$curl "https://api.etera.dev/restaurant/mcp/mcp/tools" \
>  -H "Authorization: Bearer YOUR_TOKEN"
2

Get tool details

Inspect a specific tool’s input schema to understand its parameters:

$curl "https://api.etera.dev/hotel/mcp/mcp/tools/search_hotels" \
>  -H "Authorization: Bearer YOUR_TOKEN"

The response includes the tool’s inputSchema (JSON Schema) describing all required and optional parameters.

3

Execute a tool

Call the tool with the required parameters:

$curl -X POST "https://api.etera.dev/restaurant/mcp/mcp/execute/search_restaurants" \
>  -H "Authorization: Bearer YOUR_TOKEN" \
>  -H "Content-Type: application/json" \
>  -d '{
>    "query": "Italian restaurants in Dubai",
>    "limit": 5
>  }'

Advanced Operations

Check which backend services are registered with an MCP aggregator:

$curl "https://api.etera.dev/experience/mcp/mcp/services" \
>  -H "Authorization: Bearer YOUR_TOKEN"

MCP aggregators cache tool definitions from their backend services. Force a refresh if tools have been updated:

$curl -X POST "https://api.etera.dev/flight/mcp/mcp/refresh" \
>  -H "Authorization: Bearer YOUR_TOKEN"

Check the health of any MCP aggregator:

$curl "https://api.etera.dev/restaurant/mcp/mcp/health"

Architecture

Each MCP service acts as an aggregator that discovers tools from related microservices, caches schemas for fast lookup, and routes execution calls to the appropriate backend.

AI Model → MCP Aggregator → Backend Services
                ├── Search Service
                ├── Booking Service
                └── Data Service

The aggregator pattern means you only need to integrate with one MCP endpoint per vertical, rather than connecting to each backend service individually.

AI Supervisor

For cross-vertical AI coordination, use the AI Supervisor at /ai/input. It automatically detects intent and routes to the appropriate vertical’s agents.

$curl -X POST "https://api.etera.dev/ai/input" \
>  -H "Authorization: Bearer YOUR_TOKEN" \
>  -H "Content-Type: application/json" \
>  -d '{
>    "inputType": "text",
>    "text": "Find me a hotel in Dubai near the beach"
>  }'

Next Steps

Restaurant MCP

Full MCP API reference for restaurants

AI Supervisor

Cross-vertical AI coordination API

Authentication

Get your JWT token