How to Use the ChatGen MCP in AutoGen

Q: How do I give my AutoGen agents access to ChatGen tools?

Use the autogen-extmcp package. The mcpservertools function connects to the MCP Server endpoint and returns a list of tools. You just pass this list to your AssistantAgent when you create it.

Use multi-agent debate in AutoGen to manage ChatGen bots and analyze complex lead behavior.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect ChatGen MCP to AutoGen

Create your Vinkius account to connect ChatGen 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 ChatGen with AutoGen

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Let Agents Debate Bot Strategy

Go beyond simple commands. With AutoGen, you can create a team of agents to manage your ChatGen bots. One agent, using `list_conversations`, might argue a bot's script is ineffective. Another, using data from a different tool, might defend its conversion rate. The agents converse, challenge each other's findings, and reach a consensus. The final decision might be to use `update_bot` with a new script A/B tested against the old one. This MCP Server gives your agent team the specific ChatGen data they need to form their arguments.

Multi-Agent Lead Qualification

A single agent might misinterpret a lead. AutoGen lets you build a group chat where agents collaborate on lead qualification. A "Sales Analyst" agent could use `get_lead_details` and `list_conversations` to summarize a prospect's needs. Then, a "Routing" agent, using `list_teams`, could determine the best team to handle the lead. They can even have a "Manager" agent that approves the final routing decision. It's a more reliable process because it requires agreement between multiple specialized agents.

Use AutoGen for Complex Bot Maintenance Tasks

Some tasks require multiple steps and checks. You can create an AutoGen workflow to safely delete obsolete bots. An "Auditor" agent could first use `list_bots` and `list_conversations` to confirm a bot has no recent activity. Only after the Auditor confirms the bot is safe to remove does it signal a "Janitor" agent to execute the `delete_bot` command. This conversational, multi-agent approach adds a layer of safety that's hard to achieve with a single agent.

Setup guide

Set up ChatGen 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 ChatGen 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="ChatGen_assistant",
    model_client=OpenAIChatCompletionClient(model="gpt-4o"),
    tools=tools,
)

result = await agent.run("List recent ChatGen 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="ChatGen_assistant",
        model_client=OpenAIChatCompletionClient(model="gpt-4o"),
        workbench=workbench,
    )

    result = await agent.run("List recent ChatGen 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 ChatGen. 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 ChatGen 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 ChatGen MCP in AutoGen

Use the `autogen-ext[mcp]` package. The `mcp_server_tools` function connects to the MCP Server endpoint and returns a list of tools. You just pass this list to your `AssistantAgent` when you create it.

Yes. You can provide a different list of tools to each agent in your group chat. For example, give a "BotManager" agent access to `create_bot` and `update_bot`, but restrict a "BotAuditor" agent to read-only tools like `list_bots`.

Automated reporting is a great one. Have one agent pull data using `list_leads` and `list_conversations`. A second agent analyzes that data for trends. A third agent formats the analysis into a report. They work together in a group chat to produce the final output.

One agent might propose, "I think we should update bot-123." It would call `get_bot` to get the current config as evidence. Another agent might challenge it, and the conversation continues until they agree on a plan, which might involve calling `update_bot`.

Yes. All API calls to get lead details or bot data are routed through Vinkius's zero-trust infrastructure. Each request is handled in an isolated, ephemeral session that is destroyed after the call completes. Your data isn't persisted or logged on the Vinkius platform.

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