How to Use the Maropost MCP in AutoGen

Q: How do my AutoGen agents get access to the Maropost tools?

You use the mcpservertools function from the autogen-ext library, pointing it to your Vinkius server URL. This function fetches the tools and prepares them to be passed directly into an AssistantAgent constructor.

Set up teams of AutoGen agents to debate, plan, and execute marketing strategies using live Maropost data.

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 AutoGen

Create your Vinkius account to connect Maropost 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 Maropost with AutoGen

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Create Multi-Agent Marketing Teams

This server gives your AutoGen agents the tools they need to manage Maropost. You can build a team: a 'CampaignPlanner' agent proposes a new email blast, and a 'Compliance' agent uses `list_contacts_in_list` to check the proposed segment against suppression lists. They don't just act; they converse and reach a consensus first. This collaborative approach prevents mistakes. The 'Planner' might want to use `create_contact` to add a list of prospects, but the 'Compliance' agent can stop it if the list contains invalid emails. It's a system of checks and balances for your marketing automation.

Debate and Refine Your Campaigns

Your agents can use the Maropost tools to have data-driven arguments. One agent could pull a report with `get_report_details` and argue a campaign was successful. Another agent could use `get_campaign_details` to point out the subject line was non-compliant and `list_contacts_in_list` to show it went to the wrong segment. Through this debate, the agents can formulate a better strategy for the next campaign. The final output isn't just a single action; it's a well-vetted plan that multiple specialized agents have agreed upon. This is what makes the AutoGen approach so robust.

Build a Self-Correcting MCP Server Monitor

Set up a team of agents to monitor your Maropost account. A 'Watcher' agent periodically runs `list_workflows` and `list_campaigns`. If it sees something unexpected, it brings in a 'Diagnostician' agent, which uses `get_workflow_details` and `get_campaign_details` to investigate. Based on the diagnosis, a 'Remediation' agent could be tasked to take corrective action, or the conversation could be escalated to a human user. This turns your MCP server from a simple tool executor into a proactive, self-managing system.

Setup guide

Set up Maropost 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 Maropost 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="Maropost_assistant",
    model_client=OpenAIChatCompletionClient(model="gpt-4o"),
    tools=tools,
)

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

    result = await agent.run("List recent Maropost 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 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 AutoGen

You use the `mcp_server_tools` function from the `autogen-ext` library, pointing it to your Vinkius server URL. This function fetches the tools and prepares them to be passed directly into an `AssistantAgent` constructor.

Yes. You create separate tool lists for each agent. For example, your 'Analyst' agent might only get the 'get' and 'list' tools, while your 'Operator' agent gets `create_contact`. You control this when you construct each agent.

Choose AutoGen when the right course of action isn't obvious. If your task requires multiple perspectives—like balancing marketing goals with compliance rules—a multi-agent conversation is more effective than a single-agent chain of commands. It's for solving complex, ambiguous problems.

It's based on their system message and the ongoing conversation. An agent designed for analysis will naturally gravitate towards using `get_report_details`, while an agent built for execution will look for opportunities to use `create_contact`. The conversation history provides the context for their next move.

The Vinkius platform secures the actual API call to Maropost, processing data like contact lists within a temporary, isolated environment. The tool's output—like a list of campaigns from `list_campaigns`—is then passed back into the AutoGen conversation. All agents in that conversation can see the data, so you should design your agent groups based on who needs to know what.

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