How to Use the Maropost MCP in LangChain

Q: How do I get started with Maropost and LangChain?

Install the necessary packages, then point the MultiServerMCPClient to your Vinkius endpoint URL. The client's gettools() method returns a list of functions you can pass directly to a LangChain agent constructor. That's it.

Q: Can my LangChain agent manage multiple Maropost accounts?

Yes. You can instantiate multiple MultiServerMCPClient objects, each with a different Vinkius endpoint token. Your agent can then decide which account's tools to use based on the task at hand.

Build and trace Maropost automation chains with your LangChain agent. See every API call, every input, every result.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Maropost MCP to LangChain

Create your Vinkius account to connect Maropost 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 Maropost with LangChain

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Chain Marketing Operations Together

This MCP server gives your LangChain agent the tools to run multi-step marketing tasks. You can build a chain that first calls `list_lists` to find a specific audience, then uses `list_contacts_in_list` to get the members, and finally runs `get_contact` to check an individual's status before adding them to a new campaign. Because it's LangChain, every step is observable. You aren't just firing off API calls into the dark. You get a full trace in LangSmith, showing exactly what your agent decided to do with the Maropost tools, what data it passed to `create_contact`, and what came back. It's how you debug complex agentic workflows.

Automate Campaign Reporting

Give your agent the job of monitoring campaign performance. It can regularly call `list_campaigns` and `list_reports` to see what's new. From there, it can dig into specifics with `get_campaign_details` and `get_report_details` to pull out metrics like open rates and clicks. The agent can then summarize this information or even use it as context for its next action, like triggering a follow-up workflow. You stop pulling reports manually; your agent does it for you and tells you what you need to know. It's a simple, effective way to keep tabs on your marketing efforts without living in the Maropost dashboard.

Manage Workflows from your Agent

This Maropost MCP Server lets your agent interact directly with marketing automation workflows. Your agent can get a complete overview using `list_workflows` and then inspect the setup of any specific one with `get_workflow_details`. This is perfect for auditing your automation or for building systems that react to workflow changes. Imagine an agent that monitors your active workflows. If it detects a change or a problem using `get_workflow_details`, it can ping you on Slack. You can even build chains that help you provision new automations by checking existing setups first, preventing duplicate or conflicting rules.

Setup guide

Set up Maropost 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 Maropost 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({
    "maropost-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 Maropost 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 Maropost. 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 Maropost 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 Maropost MCP in LangChain

Install the necessary packages, then point the `MultiServerMCPClient` to your Vinkius endpoint URL. The client's `get_tools()` method returns a list of functions you can pass directly to a LangChain agent constructor. That's it.

Yes, that's the whole point. You can create a chain where you pull campaign data with `list_campaigns`, run it through a custom Python script for analysis, and then save the results to a Google Sheet. The Maropost tools just become another component in your pipeline.

The MCP server passes the error right back to the agent. You can configure your agent's error handling logic to retry the call, try a different tool, or stop and ask for help. It's fully observable in your LangSmith traces.

Yes. You can instantiate multiple `MultiServerMCPClient` objects, each with a different Vinkius endpoint token. Your agent can then decide which account's tools to use based on the task at hand.

Your data stays between your agent, the Vinkius MCP Server, and Maropost. Vinkius uses your endpoint token for authentication and runs the tool logic in an ephemeral sandbox. The server only handles the data required for the specific tool call, like contact details for `create_contact` or campaign IDs for `get_campaign_details`.

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