How to Use the Landbot MCP in OpenAI Agents SDK

Q: How do I connect the OpenAI Agents SDK to my Landbot account?

Install the SDK, then instantiate an MCPServerStreamableHttp client with your Vinkius endpoint URL. Pass this server instance into your Agent's constructor in the mcpservers list, and the tools will be discovered automatically.

Q: Can my OpenAI agent start a specific Landbot flow for a user?

Yes. The agent can call the triggerbotflow tool. You just need to provide the ID of the bot and the target customer.

Q: What's the best way to manage multiple Landbot bots with the OpenAI Agents SDK?

Use the listactivebots tool to get a list of all running bots. Your agent can then decide which one to interact with based on its internal logic. The SDK's tracing helps you monitor these interactions across all your bots.

Q: Can an agent send a WhatsApp message through Landbot?

It can. The sendwhatsapptemplate tool lets your agent send pre-approved templates. This is perfect for notifications, appointment reminders, or other structured outbound messages.

Build production-ready conversational agents for Landbot with the safety and tracing of the OpenAI Agents SDK.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Landbot MCP to OpenAI Agents SDK

Create your Vinkius account to connect Landbot 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 Landbot with OpenAI Agents SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Automate Chatbot Workflows

Connect your OpenAI Agent to Landbot to start conversations or update user data. Your agent can `trigger_bot_flow` to kick off a specific onboarding sequence for a new user, then use `update_customer_field` to tag them in Landbot based on their answers. This isn't just fire-and-forget. The OpenAI Agents SDK gives you full tracing, so you can see every action your agent takes. If a flow fails, you'll know exactly which step broke and why, right from your OpenAI dashboard.

Manage Live Agent Handoffs

Your agent can query for available support staff using `list_team_agents` and see which bots are currently running with `list_active_bots`. If a customer's query is too complex for the bot, the agent can execute a `handoff_to_agent` call to route the conversation to a human. The SDK's guardrails are critical here. You can configure rules that prevent the agent from handing off low-priority chats, ensuring your human agents only handle the important stuff. Multi-agent handoffs let one specialized agent decide when to pass control to another, like a triage agent passing a hot lead to a sales agent.

Proactive Outreach with your OpenAI Agent

This MCP Server lets your agent send messages directly to customers. It can `send_proactive_text` for simple updates or `send_whatsapp_template` for approved, structured messages. You can build agents that re-engage users who dropped off or send follow-ups after a support interaction. Since you're using the OpenAI Agents SDK, you can build safety checks around this. For instance, your agent can first use `get_customer_details` to check if a user has opted out of communications before it even attempts to send a message. This prevents spammy behavior and keeps your system compliant.

Setup guide

Set up Landbot 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 Landbot tools at runtime.
3

Create your Agent

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

Run the agent

Call Runner.run(agent, prompt) to execute. The agent invokes the appropriate Landbot 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="Landbot Agent",
            instructions="You have access to Landbot 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 Landbot. 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 Landbot 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 Landbot MCP in OpenAI Agents SDK

Install the SDK, then instantiate an `MCPServerStreamableHttp` client with your Vinkius endpoint URL. Pass this server instance into your Agent's constructor in the `mcp_servers` list, and the tools will be discovered automatically.

Yes. The agent can call the `trigger_bot_flow` tool. You just need to provide the ID of the bot and the target customer.

Use the `list_active_bots` tool to get a list of all running bots. Your agent can then decide which one to interact with based on its internal logic. The SDK's tracing helps you monitor these interactions across all your bots.

It can. The `send_whatsapp_template` tool lets your agent send pre-approved templates. This is perfect for notifications, appointment reminders, or other structured outbound messages.

Your MCP Server only brokers requests for customer data like names and custom properties when your agent calls `get_customer_details` or `list_landbot_customers`. The data is streamed directly to your agent over a Vinkius-secured, ephemeral connection and is not stored by the server itself.

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