How to Use the Buttondown MCP in AutoGen

Q: How do I register the Buttondown MCP Server in AutoGen?

Install autogen-extmcp and use the server tools adapter. This maps the MCP tools directly to your AssistantAgent constructor.

Set up AutoGen agent debates to review, draft, and audit your Buttondown newsletters before they go live.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Buttondown MCP to AutoGen

Create your Vinkius account to connect Buttondown 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 Buttondown with AutoGen

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Run multi-agent editorial reviews in AutoGen

The `create_email` tool allows your AutoGen writer agent to save drafts directly into Buttondown after a structured debate. One agent drafts the content, while a separate editor agent reviews it for tone and clarity. This MCP integration ensures no email is ever created without passing your multi-agent quality checks first. Once they reach a consensus, the writer agent calls the tool to save the draft.

Manage lists with this collaborative MCP Server

The `create_subscriber` tool is invoked only after your AutoGen agents agree on a user's categorization. A triage agent reads raw user data, while a tagging agent checks `list_tags` to find the best match. They debate the correct placement, and only call the tool once they align. This prevents messy, redundant tag creation and keeps your list clean.

Audit campaign performance using AutoGen

The `get_email_analytics` tool feeds performance data directly into your analytical agents. An analyst agent presents the open and click rates, while a strategist agent proposes changes to the newsletter structure. The strategist agent then uses `list_emails` to compare these numbers against older campaigns. This debate produces clear, actionable feedback for your next writing cycle.

Setup guide

Set up Buttondown 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 Buttondown 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="Buttondown_assistant",
    model_client=OpenAIChatCompletionClient(model="gpt-4o"),
    tools=tools,
)

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

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

Install `autogen-ext[mcp]` and use the server tools adapter. This maps the MCP tools directly to your AssistantAgent constructor.

Yes, they can divide the labor. One agent can draft the newsletter using `create_email`, while another uses `list_tags` to verify the distribution list before final approval.

The agents debate the subscriber's profile data. If one agent wants to use `create_subscriber` but another flags a duplicate using `get_subscriber`, they resolve the conflict before making the API call.

Yes, the adapter translates the schemas automatically. You can connect your AutoGen agents to the Vinkius hosted HTTP endpoint without worrying about transport-level formatting.

Nothing is lost because Vinkius runs are ephemeral and stateless. If an agent fails mid-debate, your existing drafts and subscriber lists on Buttondown remain completely untouched.

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