How to Use the Ezus MCP in LangChain

Q: How does LangChain track errors when calling the Ezus MCP Server?

LangSmith traces every tool execution in real time. If getinvoice fails or returns a 404, you see the exact payload sent by your LangChain agent in the trace log.

Q: Can my agent search for specific travel products in Ezus?

Yes. Your agent calls listproducts to search the inventory, then uses getproduct to fetch the exact pricing and description for your travel itineraries.

Connect your LangChain agents directly to Ezus using this MCP Server to run multi-step travel booking and billing pipelines.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Ezus MCP to LangChain

Create your Vinkius account to connect Ezus 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 Ezus with LangChain

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Run multi-step Ezus booking chains in LangChain

The `upsert_project` tool lets your agent initialize or modify travel itineraries based on incoming emails or chat logs. LangChain chains this write operation directly into client lookup steps using `get_client` to verify customer profiles before updating any booking details. You get full visibility of these sequential actions in LangSmith. If a project update fails, you trace the exact inputs that went into the `upsert_project` call to debug the schema mismatch instantly.

Automate billing reconciliation with LangChain MCP Server tools

The `list_invoices` tool pulls active billing records directly into your LangChain decision loops. Your agent checks outstanding balances and matches them against supplier records by triggering `get_invoice` and `get_supplier` in a single execution chain. This setup removes the manual work of cross-referencing files. The agent evaluates the invoice status, finds the corresponding supplier details, and flags discrepancies for your team to review.

Coordinate complex supplier inventories

The `list_suppliers` tool queries your entire vendor database to find available travel partners for new itineraries. Your LangChain agent passes these supplier IDs to `list_products` to pull specific travel packages, hotels, or transit options for the draft project. Because LangChain supports multi-server aggregation, you can combine this Ezus data with external weather or flight APIs. The agent builds a complete travel plan using verified supplier rates without leaving the chain.

Setup guide

Set up Ezus 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 Ezus 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({
    "ezus-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 Ezus 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 Ezus. 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 Ezus 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 Ezus MCP in LangChain

Yes. You use MultiServerMCPClient to load the Ezus tools into your LangChain agent. The agent then passes the output of list_clients directly into upsert_project to update records sequentially.

LangSmith traces every tool execution in real time. If get_invoice fails or returns a 404, you see the exact payload sent by your LangChain agent in the trace log.

Yes. Your agent calls list_products to search the inventory, then uses get_product to fetch the exact pricing and description for your travel itineraries.

Install langchain-mcp-adapters and instantiate the client with your Vinkius endpoint. Pass the tools returned by get_tools() directly to your agent's tool list.

Yes. Vinkius runs the server in an isolated sandbox, meaning your invoices, client profiles, and supplier details are never stored on our servers. Your API token stays encrypted, and data flows directly between LangChain and Ezus.

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