How to Use the ThinkStack MCP in AutoGen

Q: What tools are required to set up multi-agent conversations?

You must use listbots and getbot first. These tools define the roles and capabilities of the individual agents that will be debating or working together.

Q: If I need to audit my setup in AutoGen, what tools are useful?

A good audit requires checking listactions (to see available functions) and running checkthinkstackstatus (to ensure the underlying API connection is stable).

Multi-Agent Debate with AutoGen: Build consensus systems using ThinkStack's tools.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers — Included with Plan

Connect ThinkStack MCP to AutoGen

Create your Vinkius account to connect ThinkStack 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 ThinkStack with AutoGen

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Facilitate Multi-Perspective Decision Making

AutoGen runs agents that debate an issue. One agent might use `get_bot` to gather facts, while another uses `send_query` to test hypotheses. They challenge each other's findings until they converge on a consensus decision. This structure is ideal when the answer isn't obvious and requires competing viewpoints—it’s built for deliberation.

Manage and Verify Agent Assets

You use `list_bots` to see every agent available in your system. The agents can then access details via `get_bot`, or run actions using the tools listed by `list_actions`. This keeps all components of the debate visible. ThinkStack ensures that every tool call is part of a structured, multi-agent conversation.

Track and Contextualize Interactions

The system uses `get_conversation` to log the entire exchange. This isn't just a transcript; it’s the record of how agents debated and reached a final conclusion. If you need to adjust the knowledge base used in the debate, `add_source` lets your team update the underlying facts.

Setup guide

Set up ThinkStack 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 ThinkStack 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="ThinkStack_assistant",
    model_client=OpenAIChatCompletionClient(model="gpt-4o"),
    tools=tools,
)

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

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

The agents decide which MCP Server tool to call and in what sequence. The output of a tool becomes part of the conversational context, feeding into the next agent's argument.

You must use `list_bots` and `get_bot` first. These tools define the roles and capabilities of the individual agents that will be debating or working together.

A good audit requires checking `list_actions` (to see available functions) and running `check_thinkstack_status` (to ensure the underlying API connection is stable).

Absolutely. The entire framework is designed for this. Agents negotiate conclusions, meaning they can pass through multiple steps of deliberation before a final output.

The server touches conversation details and bot configuration. Every action taken by an agent or tool invocation is recorded in `get_conversation`, providing auditable proof of interaction.

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