How to Use the Buttondown MCP in LangChain

Q: How do I configure the Buttondown MCP Server inside a LangChain project?

Install langchain-mcp-adapters and langgraph via pip. Instantiate the client with the Vinkius HTTP endpoint to expose the MCP tools.

Q: Can a LangChain agent manage Buttondown subscribers autonomously?

Yes, by combining listsubscribers and createsubscriber in a ReAct loop. The agent inspects your current list, determines if a user exists, and adds them with specific tags automatically.

Q: How does LangSmith help with debugging Buttondown tool calls in LangChain?

LangSmith captures every input and output for tools like createemail or getemailanalytics. You can see the exact payload sent to Buttondown and trace why an agent chose a specific draft format.

Build self-correcting newsletter workflows in LangChain by hooking your agent directly to your Buttondown lists and drafts.

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 LangChain

Create your Vinkius account to connect Buttondown to LangChain 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 LangChain

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Build multi-step draft chains in LangChain

The `create_email` tool lets your LangChain agent generate newsletter drafts directly inside your Buttondown account. You can pipe raw markdown from a previous research chain step straight into this tool without writing custom API glue code. LangSmith traces the entire flow, showing you exactly how your agent decided to format the draft before calling `get_account_info` to verify the sender profile. This MCP configuration lets you debug messy newsletter formatting issues in seconds.

Sync subscriber tags inside LangChain loops

The `create_subscriber` tool registers new readers to your newsletter right from your agent's execution flow. Your LangChain agent can fetch your current tag list using `list_tags` first, then decide which group fits the user best. Because LangChain handles multi-step reasoning, your agent can evaluate a user's incoming query, find the right audience segment, and apply the tag immediately. You don't have to build separate webhook handlers to keep your lists clean.

Analyze campaign performance with this MCP Server

The `get_email_analytics` tool pulls open rates, link clicks, and bounce metrics directly into your LangChain decision loops. Your agent uses this data to write better subject lines for the next run based on what actually worked. By linking `list_emails` with your analytics queries, the agent compares historical performance across different campaigns. This gives your automated marketing runs a real-time feedback loop based on hard numbers.

Setup guide

Set up Buttondown MCP in LangChain

Prerequisites

Python 3.10+ installed
langchain-mcp-adapters + langgraph packages
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run pip install langchain-mcp-adapters langgraph langchain-openai. The MCP adapters package converts MCP tools into native LangChain BaseTool objects.
2

Connect via HTTP transport
Use MultiServerMCPClient with "transport": "http" pointing to your Vinkius endpoint. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Create a ReAct agent
Pass the discovered tools to create_react_agent() from LangGraph. The agent automatically routes Buttondown tool calls through the MCP protocol.
4

Run with any LLM
Swap ChatOpenAI for ChatAnthropic, ChatGoogleGenerativeAI, or any LangChain-compatible model. The MCP tools work identically across all providers.

agent.py

from langchain_mcp_adapters.client import MultiServerMCPClient
from langgraph.prebuilt import create_react_agent
from langchain_openai import ChatOpenAI

async with MultiServerMCPClient({
    "buttondown-mcp": {
        "transport": "http",
        "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp",
    }
}) as client:
    tools = client.get_tools()

    agent = create_react_agent(
        ChatOpenAI(model="gpt-4o"),
        tools,
    )
    result = await agent.ainvoke({
        "messages": "List recent Buttondown transactions"
    })
    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 LangChain

Install `langchain-mcp-adapters` and `langgraph` via pip. Instantiate the client with the Vinkius HTTP endpoint to expose the MCP tools.

Yes, by combining `list_subscribers` and `create_subscriber` in a ReAct loop. The agent inspects your current list, determines if a user exists, and adds them with specific tags automatically.

LangSmith captures every input and output for tools like `create_email` or `get_email_analytics`. You can see the exact payload sent to Buttondown and trace why an agent chose a specific draft format.

Absolutely. You can combine this server with database or vector store tools in a single LangChain agent. The agent will query your database and then use `create_email` to draft the newsletter.

Vinkius runs the server in an isolated, zero-trust V8 sandbox that destroys itself after execution. This secure MCP environment ensures your subscriber emails and list metrics are never cached or exposed to other tenants.

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