How to Use the SmartChatAI MCP in AutoGen

Q: Can I make my AutoGen system use SmartChatAI's knowledge base?

Yes. You can first train the bot using addpdftoknowledgebase or addwebsitetoknowledgebase. The agents then reference this specialized data when debating a solution.

Q: What data does SmartChatAI touch when managing bots in AutoGen?

It manages bot creation via createnewaibot, retrieves detailed configuration using getchatbotdetails, and tracks all conversation flow through listaichatbots.

Q: What data does SmartChatAI touch when listing webhooks in AutoGen?

The listconfiguredwebhooks tool allows the debating agents to survey which external systems are already connected, adding a layer of system awareness to their conversation.

Achieve consensus decisions with AutoGen using the SmartChatAI MCP Server.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers — Included with Plan

Connect SmartChatAI MCP to AutoGen

Create your Vinkius account to connect SmartChatAI to AutoGen — we handle the hosting, security, and runtime updates so you don't have to. No server setup required.

GDPR Included with Plan

Setup SmartChatAI with AutoGen

Ask AI about this MCP

ChatGPT

Claude

Perplexity Vinkius runs on Gemini

Gemini

Grok

Multi-Agent Decision Making

AutoGen's strength is debate. You can set up agents that challenge each other on a goal, and they use `message_ai_chatbot` as the primary tool for generating proposals. One agent might suggest an action, while another critiques its feasibility. The MCP Server provides the shared workspace where this deliberation happens. The final 'consensus' is achieved through multiple rounds of structured communication using the available tools.

State-Aware Workflow Testing

Before making a decision, your agents need to know what exists. They can use `list_ai_chatbots` and then individually call `get_chatbot_details` for each bot ID found. This gives the entire group a complete picture of available assets. The MCP Server's tools allow you to simulate complex workflows where one agent checks system health (`check_api_health`), passes that status, and another decides whether proceeding is safe.

Contextual Data Gathering

The agents can gather context for their debate. One might use `scrape_domain_links` to collect data points, while another uses `get_bot_chat_history` to review past decisions. This provides all necessary inputs for a deep, reasoned discussion. The MCP Server ensures that these diverse pieces of information—from links to chat logs—are available in the shared conversational memory for debate.

Setup guide

Set up SmartChatAI 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 SmartChatAI 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="SmartChatAI_assistant",
    model_client=OpenAIChatCompletionClient(model="gpt-4o"),
    tools=tools,
)

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

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

AutoGen feeds the MCP Server tools list into its agents. The agents then decide which tool to invoke during their conversation flow, passing inputs and receiving outputs back into the debate.

Yes. You can first train the bot using `add_pdf_to_knowledge_base` or `add_website_to_knowledge_base`. The agents then reference this specialized data when debating a solution.

It manages bot creation via `create_new_ai_bot`, retrieves detailed configuration using `get_chatbot_details`, and tracks all conversation flow through `list_ai_chatbots`.

It's designed for it. The tools provide discrete, callable actions that multiple agents can interact with and debate over, forcing consensus on an outcome.

The `list_configured_webhooks` tool allows the debating agents to survey which external systems are already connected, adding a layer of system awareness to their conversation.

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