Skip to main content
Use this pageChatGPTClaudeCursor · OpenAPI · MCP

Use with AI

Connect does not ship official HTTP SDKs. Assistants should read the contract and OpenAPI, then generate a client in your language. A second “docs MCP” is unnecessary.

Two different tools:

GoalUse
Generate a production clientContract card + OpenAPI YAML (widget below)
Let a chat agent call search/quote/bookBooking MCP (Streamable HTTP)

Do not use MCP as a codegen source of truth. Do not book production inventory from a Custom GPT Action.

Path to a working integration

Six steps, same wire as production. Copy identifiers literally. Do not invent fields.

  1. 1

    Create a sandbox key

    sk_test_* from the Connect console. Never send it as X-API-Key.

    Console
  2. 2

    Resolve hotels, then search

    Content API for catalog codes. Availability has no destination field — send criteria.hotels.

    Search
  3. 3

    Quote first; skip only without RECHECK

    Quote by default. Book from search only when no RATE_TYPE remark contains RECHECK and that connection allows it. Handoff search options[].id → quote optionRefId.

    Quote
  4. 4

    Book and persist bookingID

    Book with optionQuote.optionRefId. Read booking.reference.bookingID. Status is BOOK_STATUS_TYPE_*.

    Book
  5. 5

    Treat HTTP 200 as maybe-failed

    Inspect errors[] (ERR_CODE_* / ERR_TYPE_*). Gateway 401/403/429 is a different envelope.

    Errors
  6. 6

    Point the IDE at the contract

    AGENTS.md + OpenAPI YAML. Optional booking MCP for agents that call the funnel live.

    Use with AI

Authenticate once

Buyer header is Authorization with an ApiKey prefix. Sandbox keys only work on the test host.

HeaderAuthorization: ApiKey sk_test_*
Sandbox hosthttps://test-api.bundleport.com
Authentication guideOpen console

OpenAPI — generate the client

Stable YAML for OpenAPI Generator, Postman, Insomnia, and IDE plugins. Import the file; do not install unpublished SDK packages.

Booking APIhttps://docs.bundleport.com/openapi/hotels.yaml
Content APIhttps://docs.bundleport.com/openapi/content.yaml
llms-full.txthttps://docs.bundleport.com/llms-full.txt
Download booking YAMLDownload content YAMLTry search in the docs

Build with your assistant

There is no official HTTP SDK. Point Cursor, ChatGPT, or Claude at the contract and OpenAPI, then generate a client in your language.

Cursor

Index the docs and drop AGENTS.md in the buyer repo. Optional: install booking MCP for live search/quote/book.

MCP install

ChatGPT

Opens a chat preloaded with the contract, OpenAPI URL, auth header, and fields you must not invent.

Open in ChatGPTllms.txt

Claude

Same prompt as ChatGPT. Prefer project knowledge plus OpenAPI over executing book from a custom action in production.

Open in ClaudeBooking YAML
Contract card

Install booking MCP

Streamable HTTP at the aggregator. Tools: availability, quote, book, bookingDetail, cancel. Same identifiers as REST. Set BUNDLEPORT_API_KEY in the environment; the install snippet uses ${env:BUNDLEPORT_API_KEY}. Do not commit sk_*.

Add to CursorAdd to VS Code
MCP endpointhttps://api.connect.bundleport.com/mcp
{
  "mcpServers": {
    "bundleport-hotels": {
      "url": "https://api.connect.bundleport.com/mcp",
      "headers": {
        "Authorization": "ApiKey ${env:BUNDLEPORT_API_KEY}"
      }
    }
  }
}

Cursor​

  1. Docs: Settings → Indexing & Docs → add https://docs.bundleport.com (or @Docs this site).
  2. Rules: copy AGENTS.md into the buyer repo as AGENTS.md (or a project rule that says “follow that file”).
  3. Optional booking MCP (runtime only) — use Add to Cursor in the widget above. Put the key in env; do not commit it.

Use sk_test_* until the agent is restricted. MCP tools are availability, quote, book, bookingDetail, cancel.

ChatGPT​

  • Knowledge / codegen: upload or fetch llms-full.txt plus openapi/hotels.yaml. Prefer generating REST code over Actions that execute book in production.
  • Custom GPT Actions (test only): import https://docs.bundleport.com/openapi/hotels.yaml, server https://test-api.bundleport.com, auth header Authorization: ApiKey sk_test_*. Never attach sk_prod_*.

Claude​

  • Project knowledge: add https://docs.bundleport.com/llms.txt and the contract URL. Fetch OpenAPI when writing code.
  • Claude Code: project instruction = AGENTS.md. Optional MCP booking endpoint as above.

Gemini​

Gem or URL context: https://docs.bundleport.com/llms.txt and https://docs.bundleport.com/openapi/hotels.yaml. Paste the contract card if the context window is tight.

Any language (OpenAPI Generator / curl)​

Generate types from the YAML, or call REST directly. Always parse errors[] on HTTP 200. Search occupancies use age only. There is no destination field on availability — resolve hotel codes via the Content API, then send criteria.hotels as in Search.

const res = await fetch('https://test-api.bundleport.com/connect/hotels/v1/availability', {
  method: 'POST',
  headers: {
    Authorization: `ApiKey ${process.env.BUNDLEPORT_API_KEY}`,
    'Content-Type': 'application/json',
  },
  body: JSON.stringify({
    criteria: {
      checkIn: '2026-11-01T00:00:00Z',
      checkOut: '2026-11-03T00:00:00Z',
      occupancies: [{ paxes: [{ age: 30 }, { age: 30 }] }],
      hotels: ['12345'],
      currency: 'EUR',
      language: 'en',
    },
    settings: {
      connectionCodes: ['testb-conn-1876'],
      timeout: 10000,
    },
  }),
});
const data = await res.json();
if (!res.ok) throw new Error(`HTTP ${res.status}`);
if (Array.isArray(data.errors) && data.errors.length) {
  console.error(data.errors);
}

Quickstart has full occupancy and book examples. HTTP clients — no published SDK packages.