How to Use the Lamha MCP in OpenAI Agents SDK

Q: How do I connect Lamha to the OpenAI Agents SDK?

Initialize MCPServerStreamableHttp with your Lamha endpoint token. Pass it to the mcpservers array in your Agent constructor. The SDK handles auto-discovery for all eight tools automatically.

Q: Can OpenAI Agents SDK trace Lamha tool calls?

Yes. The dashboard logs every interaction with createorder or listorders. You see the raw Arabic input, the dialect mapping, and the exact JSON payload sent to the endpoint.

Q: Does the OpenAI Agents SDK cache Lamha's tool definitions?

Setting cacheToolsList=True stores the schemas for tools like listwarehouses locally. This cuts down initialization time when spinning up multiple specialized agents.

Q: How do I restrict an agent to read-only logistics data?

Create a dedicated agent and only expose getorder and checkcitycoverage. Keep mutation tools away from public-facing bots using OpenAI's built-in guardrails.

Build production-ready Arabic e-commerce bots with the OpenAI Agents SDK and Lamha's logistics tools.

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 OpenAI Agents SDK

Create your Vinkius account to connect Lamha to OpenAI Agents SDK 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 OpenAI Agents SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Run the Lamha MCP Server for order ops

The Lamha MCP server exposes `create_order` and `cancel_order` tools directly to your OpenAI agent. You define the safety constraints in Python while the model handles Arabic dialect parsing. Setting `cacheToolsList=True` ensures your agent discovers the `get_order` tool instantly during initialization. Tracing in the OpenAI dashboard shows exactly how the model mapped a Gulf Arabic text into a structured logistics payload.

Build specialized routing agents

Handoffs let you isolate logistics tasks by giving a specific agent access to `check_city_coverage` and `list_carriers`. The model reads the user's city in local dialect, checks coverage, and returns the available delivery options. You keep production guardrails tight. The routing agent can read data with `list_warehouses` but cannot trigger fulfillment without passing control back to a supervisor agent.

Validate stock levels in real time

Your agent checks stock using the `list_inventory` tool before confirming any user requests. OpenAI's native validation guarantees the agent formats the query correctly before hitting the Lamha endpoint. Customers ask about product availability in their native Arabic dialect. The system maps that intent, queries the specific warehouse, and replies with accurate counts without hallucinating numbers.

Setup guide

Set up Lamha MCP in OpenAI Agents SDK

Prerequisites

Python 3.10+ installed
openai-agents package (pip install openai-agents)
Active Vinkius subscription with a valid endpoint token

1

Install the SDK

Run pip install openai-agents to install the OpenAI Agents SDK. The MCP integration is built-in — no extra dependencies needed.
2

Connect via SSE transport

Use MCPServerSse with your Vinkius endpoint URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. The SDK auto-discovers all Lamha tools at runtime.
3

Create your Agent

Pass the MCP to Agent(mcp_servers=[server]). The agent receives Lamha tools as native definitions — JSON schemas resolve automatically.
4

Run the agent

Call Runner.run(agent, prompt) to execute. The agent invokes the appropriate Lamha tools and returns structured results. Copy the full example on the right to get started.

agent.py

import asyncio
from agents import Agent, Runner
from agents.mcp import MCPServerSse

async def main():
    async with MCPServerSse(
        url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    ) as server:
        agent = Agent(
            name="Lamha Agent",
            instructions="You have access to Lamha tools.",
            mcp_servers=[server],
        )
        result = await Runner.run(agent, "List recent transactions")
        print(result.final_output)

asyncio.run(main())

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 OpenAI Agents SDK

Initialize `MCPServerStreamableHttp` with your Lamha endpoint token. Pass it to the `mcp_servers` array in your Agent constructor. The SDK handles auto-discovery for all eight tools automatically.

Yes. The dashboard logs every interaction with `create_order` or `list_orders`. You see the raw Arabic input, the dialect mapping, and the exact JSON payload sent to the endpoint.

Setting `cacheToolsList=True` stores the schemas for tools like `list_warehouses` locally. This cuts down initialization time when spinning up multiple specialized agents.

Create a dedicated agent and only expose `get_order` and `check_city_coverage`. Keep mutation tools away from public-facing bots using OpenAI's built-in guardrails.

Vinkius isolates your session in an ephemeral V8 sandbox. When your agent calls `create_order`, the payload containing Arabic customer names and Middle Eastern delivery addresses passes through zero-trust architecture. Nothing persists after the client drops the connection.

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