MCP Server

The MCP server enables AI assistants to run any operation on your account, by leveraging all the API endpoints made available.

Endpoint

The LiteAPI MCP server is available at:

https://mcp.liteapi.travel/api/mcp?apiKey=YOUR_API_KEY

You must replace YOUR_API_KEY with your valid LiteAPI API key.

Example (sandbox):

https://mcp.liteapi.travel/api/mcp?apiKey=sand_xxxxxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx

⚠️ Never expose production API keys in client-side applications.

What Is MCP?

MCP (Model Context Protocol) is a standardized way for AI models to:

• Discover available tools
• Call APIs in a structured format
• Receive machine-readable responses
• Perform multi-step workflows safely

The LiteAPI MCP server wraps LiteAPI functionality as structured tools that AI systems can call deterministically.

Supported Capabilities

The MCP server exposes LiteAPI features such as:

• Hotel search
• Price and availability lookup
• Place search
• Hotel details retrieval
• Prebooking
• Booking flows

Available tools may evolve as LiteAPI expands AI capabilities.

Authentication

Authentication is handled via your LiteAPI API key:

?apiKey=YOUR_API_KEY

• Each request must include a valid API key
• Sandbox and production keys must match their respective environments
• Rate limits apply as per your API plan

Example Configuration (AI Tooling)

For AI frameworks that support MCP servers, configure the endpoint as follows:

{
  "mcpServers": {
    "liteapi": {
      "url": "https://mcp.liteapi.travel/api/mcp?apiKey=YOUR_API_KEY"
    }
  }
}

Replace YOUR_API_KEY with your actual LiteAPI key.

Rate Limits & Usage

The MCP server follows standard LiteAPI API policies:

• Default rate limit: 500 requests per second
• HTTP 429 returned when rate limited
• Usage billed according to endpoint pricing
• Monitoring available in the LiteAPI dashboard

Security Considerations

When integrating AI systems with LiteAPI MCP:

• Store API keys securely (e.g., environment variables or secret managers)
• Do not embed keys in client-side code
• Implement retry and backoff logic
• Monitor agent behavior to prevent excessive calls