How to Use the Typebot MCP in AutoGen

Q: What if I need to verify bot availability with AutoGen?

The agents can run a check using listtypebots and then use publishtypebot as part of their consensus action, ensuring the change is deployed correctly after deliberation.

Achieve consensus decisions using Typebot and AutoGen's debate framework.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Typebot MCP to AutoGen

Create your Vinkius account to connect Typebot to AutoGen 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 Typebot with AutoGen

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Negotiating Bot Status Changes

Multiple agents can discuss the best course of action for a bot. For instance, one agent proposes calling `delete_typebot` based on performance data, while another challenges it using details from `get_typebot_details`. The debate converges on a final decision. This makes your multi-agent system far more reliable than single-path execution.

Simulating Bot Flow Testing

You can use `start_chat_session` to simulate an entire interaction. The AutoGen framework then has multiple agents debate the *meaning* of that chat session, identifying potential ambiguities or logical gaps in the bot's flow. It’s like having a panel review your chatbot script for flaws before you launch it.

Debating Data Requirements

The `list_typebot_results` output provides the data. Different agents can then debate what that data actually means. One agent might argue, 'This indicates a payment issue,' while another argues, 'No, this is just confusion about the billing cycle.' It turns raw statistics into actionable, debated insights.

Setup guide

Set up Typebot MCP in AutoGen

Prerequisites

Python 3.10+ installed
autogen-ext[mcp] package
Active Vinkius subscription with a valid endpoint token

1

Install AutoGen with MCP
Run pip install "autogen-ext[mcp]" autogen-agentchat. The MCP extension includes mcp_server_tools for stateless tool access.
2

Fetch tools from the MCP
Call mcp_server_tools(SseServerParams(url=...)) with your Vinkius endpoint. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Run your agent
Pass the tools to AssistantAgent and call agent.run(). The agent invokes Typebot tools and returns structured results.

agent.py

from autogen_ext.tools.mcp import SseServerParams, mcp_server_tools
from autogen_agentchat.agents import AssistantAgent
from autogen_ext.models.openai import OpenAIChatCompletionClient

server_params = SseServerParams(
    url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
)

tools = await mcp_server_tools(server_params)

agent = AssistantAgent(
    name="Typebot_assistant",
    model_client=OpenAIChatCompletionClient(model="gpt-4o"),
    tools=tools,
)

result = await agent.run("List recent Typebot data")
print(result.messages[-1].content)

Get your connection token →

Prerequisites

Python 3.10+ installed
autogen-ext[mcp] + autogen-agentchat
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Same packages as above. McpWorkbench is ideal when your agent needs stateful sessions across multiple tool calls.
2

Use McpWorkbench as context manager
Wrap your agent in async with McpWorkbench(...) to maintain shared state and resources. The workbench manages the full MCP session lifecycle.
3

Run with workbench
Pass workbench=workbench to your agent. State is preserved across multiple tool calls within the same session.

agent.py

from autogen_ext.tools.mcp import McpWorkbench, SseServerParams
from autogen_agentchat.agents import AssistantAgent
from autogen_ext.models.openai import OpenAIChatCompletionClient

server_params = SseServerParams(
    url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
)

async with McpWorkbench(server_params) as workbench:
    agent = AssistantAgent(
        name="Typebot_assistant",
        model_client=OpenAIChatCompletionClient(model="gpt-4o"),
        workbench=workbench,
    )

    result = await agent.run("List recent Typebot data")
    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 Typebot. 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 Typebot 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 Typebot MCP in AutoGen

AutoGen uses Typebot's tools to feed evidence into the debate. If an agent needs confirmation on a bot's structure, it calls `get_typebot_details`, and that output becomes core material for the agents to argue over.

Yes. Your multi-agent system can coordinate by first calling `list_workspaces` and then having different specialized agents focus on specific, isolated bot groups within those workspaces.

The debate process centers around the collected user responses. Agents challenge each other's interpretations of the `list_typebot_results` output until a consensus is reached on the root cause of poor performance.

The agents can run a check using `list_typebots` and then use `publish_typebot` as part of their consensus action, ensuring the change is deployed correctly after deliberation.

This MCP Server touches collected user responses. When running a debate, your agent must ensure that only necessary metadata from these responses are passed to the competing agents.

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