How to Use the Magic Minutes MCP in AutoGen

Q: How do I configure Magic Minutes tools for AutoGen?

Run pip install -U "autogen-extmcp". Pass your Vinkius URL to StreamableHttpServerParams inside mcpservertools(), then hand that list to your AssistantAgent.

Q: How do I stop an AutoGen agent from spamming Magic Minutes tasks?

Require human-in-the-loop approval for the createtask tool. Set your agent's execution policy to prompt for confirmation before it writes data.

Let your AutoGen agents debate and assign tasks using the Magic Minutes MCP Server.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Magic Minutes MCP to AutoGen

Create your Vinkius account to connect Magic Minutes 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 Magic Minutes with AutoGen

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Multi-Agent Meeting Analysis via MCP

The `get_meeting_minutes` tool supplies raw transcripts to your AutoGen conversation loop. A summarization agent reads the text, while a critical-thinking agent challenges the summary for accuracy. They debate the meaning before finalizing the notes. This consensus-driven approach catches errors a single agent misses. The system negotiates the final output based on the exact words spoken. You get a highly refined summary born from competing perspectives.

Consensus-Driven Task Creation

Calling `create_task` happens only after the agents agree on who owns the work. One agent proposes an assignment based on the transcript. A second agent verifies the name using `list_contacts` and `list_meeting_attendees`. If the second agent spots a conflict—like two people with the same first name—it pushes back. The agents resolve the ambiguity before executing the write operation. You avoid misassigned work entirely.

Audit Webhooks and Folders

The `list_webhooks` tool lets a security-focused agent audit where meeting data flows. It checks the active endpoints and flags anything suspicious to the rest of the swarm. Meanwhile, an organizer agent calls `list_folders` to figure out where to file the new summary. The MCP Server handles the schema conversion automatically, so the agents just read the JSON and make decisions.

Setup guide

Set up Magic Minutes 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 Magic Minutes 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="Magic Minutes_assistant",
    model_client=OpenAIChatCompletionClient(model="gpt-4o"),
    tools=tools,
)

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

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

Run `pip install -U "autogen-ext[mcp]"`. Pass your Vinkius URL to `StreamableHttpServerParams` inside `mcp_server_tools()`, then hand that list to your `AssistantAgent`.

Yes. You provide the tool list to any agent in the swarm. The `McpToolAdapter` handles the routing and schema translation behind the scenes.

Require human-in-the-loop approval for the `create_task` tool. Set your agent's execution policy to prompt for confirmation before it writes data.

The integration supports both stdio and Streamable HTTP. Use the HTTP transport to connect directly to your managed Vinkius instance.

Contact lists and user profiles are accessed via an isolated, ephemeral V8 environment. The server processes the request, delivers the payload to your swarm, and immediately terminates.

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