How to Use the ChatFly MCP in AutoGen

Q: Can I have one AutoGen agent create a ChatFly bot and another one test it?

Yes, that's a perfect use case. The first agent calls createbot. The second agent takes the bot ID from the conversation history and uses the chat tool to run a test conversation, reporting the results back to the group.

Q: What's a practical workflow for ChatFly and AutoGen?

Set up a 'provisioner' agent that can use createbot. Add a 'QA' agent that can use getbot and chat. Finally, include a UserProxyAgent for human approval. The agents will then discuss, create, and test bots, only asking for your input when needed.

Use a team of AutoGen agents to collaboratively build and manage your ChatFly chatbots.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect ChatFly MCP to AutoGen

Create your Vinkius account to connect ChatFly 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 ChatFly with AutoGen

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Let Agents Debate Bot Strategy

The `create_bot` tool gives your agents the power to propose and build new chatbots. One agent can act as a "creator," suggesting a new bot for lead generation. Then, a "reviewer" agent can use `get_bot` to inspect the proposal. It can challenge the welcome message or name, starting a conversation that leads to a better result before anything goes live. This is collaborative decision-making, not just automation.

Delegate Bot Maintenance

The `list_bots` tool provides an inventory for your agent team to work from. A "maintenance" agent could be tasked with periodically checking all bots. It would use `list_data_sources` to see if a bot has the latest knowledge base. If not, it can propose an update with `upload_data_source`. A human-in-the-loop can then give the final approval before the change is made.

Build an AutoGen QA Team

The `chat` tool allows one of your agents to take on the role of a user. It can talk to a newly created or updated bot to make sure it's responding correctly. This is how you build a robust testing process with this MCP server. The "tester" agent reports its findings back to the group. If the conversation reveals a problem, the agents can debate the cause and use `update_bot` to fix it.

Setup guide

Set up ChatFly 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 ChatFly 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="ChatFly_assistant",
    model_client=OpenAIChatCompletionClient(model="gpt-4o"),
    tools=tools,
)

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

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

You pass the list of ChatFly tools to each AssistantAgent. Then, in your prompts, you assign roles. For example, tell one agent its job is to use `create_bot` and another that its job is to use `get_bot` to review creations.

Yes, that's a perfect use case. The first agent calls `create_bot`. The second agent takes the bot ID from the conversation history and uses the `chat` tool to run a test conversation, reporting the results back to the group.

Set up a 'provisioner' agent that can use `create_bot`. Add a 'QA' agent that can use `get_bot` and `chat`. Finally, include a `UserProxyAgent` for human approval. The agents will then discuss, create, and test bots, only asking for your input when needed.

You get a full suite of seven tools for bot management. Your agents can use `create_bot`, `get_bot`, `list_bots`, `update_bot`, `list_data_sources`, `upload_data_source`, and `chat`.

Agent conversations happen in a secure sandbox. Vinkius ensures that the ChatFly bot names, welcome messages, and any data source content discussed by your agents are processed in a zero-trust environment and are never logged or stored.

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