How to Use the IATA Developer Portal MCP in LangChain

Build LangChain pipelines that query real-time aviation data and route airport details directly into your agent chains.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect IATA Developer Portal MCP to LangChain

Create your Vinkius account to connect IATA Developer Portal to LangChain and route execution through our secure gateway. The platform manages server hosting, runtime updates, and security layers. Configuration requires no manual server provisioning.

GDPR Free for Subscribers

Setup IATA Developer Portal with LangChain

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Chain-linked aviation lookups

The `search_airports` tool lets your LangChain agent pull exact airport codes and feed them directly into downstream prompt templates. This prevents your pipelines from breaking when users enter slang or misspelled city names. You can chain the output of `search_airlines` with other tools in your run. LangSmith traces every step, showing you the exact inputs and outputs of each MCP call.

Multi-step aircraft audits

The `search_aircraft` tool retrieves technical specifications for specific plane models during your LangChain agent's execution loop. Your agent reads the output to calculate fleet metrics or verify equipment types. By combining this with `get_city_details`, your agent handles complex routing logic. The framework manages the state while the MCP server provides the ground truth.

LangChain agent validation loops

The `check_api_status` tool verifies the connection to the aviation registry before your long-running chain starts. If the API is down, your agent stops immediately instead of burning tokens on failed calls. Use `list_iata_countries` to restrict agent search space to active regions. This keeps your LangChain memory footprint small and prevents hallucinated flight paths.

Setup guide

Set up IATA Developer Portal MCP in LangChain

Prerequisites

Python 3.10+ installed
langchain-mcp-adapters + langgraph packages
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run pip install langchain-mcp-adapters langgraph langchain-openai. The MCP adapters package converts MCP tools into native LangChain BaseTool objects.
2

Connect via HTTP transport
Use MultiServerMCPClient with "transport": "http" pointing to your Vinkius endpoint. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Create a ReAct agent
Pass the discovered tools to create_react_agent() from LangGraph. The agent automatically routes IATA Developer Portal tool calls through the MCP protocol.
4

Run with any LLM
Swap ChatOpenAI for ChatAnthropic, ChatGoogleGenerativeAI, or any LangChain-compatible model. The MCP tools work identically across all providers.

agent.py

from langchain_mcp_adapters.client import MultiServerMCPClient
from langgraph.prebuilt import create_react_agent
from langchain_openai import ChatOpenAI

async with MultiServerMCPClient({
    "iata-developer-portal-mcp": {
        "transport": "http",
        "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp",
    }
}) as client:
    tools = client.get_tools()

    agent = create_react_agent(
        ChatOpenAI(model="gpt-4o"),
        tools,
    )
    result = await agent.ainvoke({
        "messages": "List recent IATA Developer Portal transactions"
    })
    print(result["messages"][-1].content)

Get your connection token →

Independent Platform Disclaimer: Vinkius is an independent platform and is not affiliated with, endorsed by, sponsored by, verified by, or otherwise authorized by IATA Developer Portal. All third-party trademarks, logos, and brand names are the property of their respective owners. Their use on this website is strictly for informational purposes to identify service compatibility and interoperability.

Why Choose Vinkius

Vinkius connects your tools to AI with real-time monitoring and automatic cost savings — all from one dashboard.

Connect IATA Developer Portal now

Real-time monitoring

Live

visibility into every interaction

Connect your favorite tools to your AI and see exactly what's happening — every request, every response, in real time.

Built-in savings

60%

lower AI costs

Vinkius compresses data between your apps and your AI automatically. Lower bills every month — no configuration required.

Single dashboard

One

place for every integration

Every tool your AI connects to, managed from a single screen. One account, complete control.

Common questions about IATA Developer Portal MCP in LangChain

The server returns standard HTTP status codes. Your LangChain agent handles retries using its built-in runnable configuration or custom exception handlers.

Yes. You can load this MCP server alongside database tools using the MultiServerMCPClient to let your agent mix aviation data with internal reservation records.

Vinkius manages the authentication token. You only configure the single secure endpoint in your MultiServerMCPClient setup.

Yes, it does. You can store retrieved airport codes in your graph state to pass them between nodes.

Vinkius runs the MCP server in an ephemeral, zero-trust sandbox. Your search queries for airport and aircraft codes are never written to persistent disks.

Use it with your favorite AI tools

Connect this server to Cursor, Claude, VS Code, and more.

OpenAI Agents SDK sdk-python

Google ADK sdk-python

Pydantic AI sdk-python

Vercel AI SDK sdk-typescript