How to Use the Lamha MCP in LangChain

Q: How do I create an order and then check its status using Lamha and LangChain?

You build an agent with access to Lamha's createorder and getorder tools. After the agent calls createorder, the resulting orderid is available in the chain's context, so the agent can immediately use it to call getorder.

Q: Can a LangChain agent decide between different carriers from Lamha?

Yes. The agent can call listcarriers, process the results (like cost and delivery time), and then use that information to select the best carrier when it calls createorder. This logic is part of the agent's reasoning process.

Q: What's the best way to handle inventory checks with Lamha and LangChain?

Give your agent the listinventory tool. Before attempting to create an order, the agent can call it to verify stock for the requested items. This prevents failed orders due to out-of-stock products.

Build logistics chains for Arabic e-commerce with LangChain. Connect Lamha's tools to create multi-step agent workflows.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Lamha MCP to LangChain

Create your Vinkius account to connect Lamha 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 Lamha with LangChain

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Chain Logistics Operations Together

Your agent can now think in steps. First, it calls `list_inventory` to confirm stock. Then, it uses `create_order` to place the order. Finally, it confirms the details with `get_order`. This isn't just a single API call. With LangChain, you build sequences where the output of one Lamha tool becomes the input for the next. The agent handles passing the `product_id` from inventory to the order form, and the `order_id` from the creation step to the lookup step. It just works.

Autonomous Order Management with the LangChain MCP Server

Stop hard-coding business logic. Use a ReAct agent that decides for itself which Lamha tool to use based on the user's request in Arabic. The agent can distinguish between a query to 'cancel my last shipment' and 'where are my packages?' It knows to call `cancel_order` for the first and `list_orders` for the second. You provide the tools and the objective. The agent figures out the path, giving you a more flexible and responsive system without writing endless if/else statements.

Trace Every Tool Call

Figure out exactly what your agent did. LangChain gives you full observability into every call made to the Lamha MCP server. You see the exact inputs for `create_order` and the `order_id` it returned. This makes debugging simple. If an order fails, you can trace the entire chain of thought—from checking `check_city_coverage` to the final failed API call—and see precisely where things went wrong. No more guesswork.

Setup guide

Set up Lamha 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 Lamha 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({
    "lamha-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 Lamha 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 Lamha. 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 Lamha 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 Lamha MCP in LangChain

You build an agent with access to Lamha's `create_order` and `get_order` tools. After the agent calls `create_order`, the resulting `order_id` is available in the chain's context, so the agent can immediately use it to call `get_order`.

Yes. The agent can call `list_carriers`, process the results (like cost and delivery time), and then use that information to select the best carrier when it calls `create_order`. This logic is part of the agent's reasoning process.

Give your agent the `list_inventory` tool. Before attempting to create an order, the agent can call it to verify stock for the requested items. This prevents failed orders due to out-of-stock products.

It does. Lamha is designed to understand queries in various Middle Eastern dialects. LangChain passes the natural language query to the MCP server, where Lamha's NLU processes it before executing a tool.

Your customer order data, including addresses and contents, is processed ephemerally. Vinkius proxies the request to the Lamha server, which performs the operation and returns the result. No order data is stored by Vinkius or persisted after the transaction completes.

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