How to Use the Landbot MCP in OpenAI Agents SDK

Q: How does the OpenAI Agents SDK handle routing a customer in Landbot?

It uses the searchcustomers and assignagent tools. Your agent finds the customer record in Landbot, then triggers the assignment to a live human agent based on your defined logic. This entire MCP interaction is logged in the OpenAI dashboard.

Q: What's the best way to find a customer with the OpenAI Agents SDK and Landbot?

Use searchcustomers with an email for a direct hit. If you don't have an email, your agent can use listcustomers and then filter the results based on other known data points like name or recent activity.

Build production-grade conversational agents for Landbot with the OpenAI Agents SDK. Your agent can find customers and route chats safely.

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

Find Customers, Route Conversations

Your agent can find specific users in Landbot. It uses `search_customers` by email or pulls from `list_customers` to identify who it's talking to. This isn't a blind chatbot; it knows the context. Once the customer is identified, your agent decides what to do. It can fetch the conversation history with `get_messages` or immediately hand off to a human with `assign_agent`. The OpenAI SDK's guardrails mean you can define rules to prevent it from assigning the wrong agent.

Send Messages from Your Agent

Let your agent send messages directly into a Landbot chat. The `send_text_message` tool allows your agent to programmatically respond to users, confirm actions, or provide information without human intervention. This works well for automated follow-ups or status updates. For example, after an agent uses `assign_agent`, another specialized agent can monitor the ticket and use `send_text_message` to notify the user when their issue is resolved. The SDK's multi-agent handoff makes this work.

Inspect Bots via this MCP Server

Your agent gets a full view of your Landbot setup. It can pull a complete inventory of your chatbots using `list_bots`, which is the starting point for any dynamic routing logic. From there, it can drill down into a specific bot's configuration with `get_bot`. Your agent can use this data to make smarter decisions, like choosing the right bot for a specific user query, all managed through this MCP Server.

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

It uses the `search_customers` and `assign_agent` tools. Your agent finds the customer record in Landbot, then triggers the assignment to a live human agent based on your defined logic. This entire MCP interaction is logged in the OpenAI dashboard.

Yes. The SDK has built-in guardrails. You can set rules that validate your agent's plan to use `send_text_message` before it executes, preventing spam or accidental duplicate messages.

Use `search_customers` with an email for a direct hit. If you don't have an email, your agent can use `list_customers` and then filter the results based on other known data points like name or recent activity.

The OpenAI dashboard provides full tracing for agent actions. Every call to a tool on this MCP server, like `get_messages` or `assign_agent`, is logged, so you have a complete audit trail.

This server only handles customer metadata, IDs, and message content via tools like `get_customer` and `get_messages`. Vinkius processes this data in an ephemeral sandbox, and your endpoint token is the only credential needed. No PII is 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