How to Use the Ecomail MCP in AutoGen

Q: How do I add Ecomail tools to an AutoGen agent?

Initialize your HTTP transport with StreamableHttpServerParams and fetch the tools via mcpservertools. Pass that directly to your AssistantAgent constructor.

Give your AutoGen multi-agent squads access to Ecomail so they can debate campaign strategies and audit subscriber lists.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Ecomail MCP to AutoGen

Create your Vinkius account to connect Ecomail 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 Ecomail with AutoGen

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Multi-Agent Campaign Strategy with AutoGen

AutoGen agents can debate your email marketing strategy by pulling real data through this MCP Server. A performance agent calls `list_latest_marketing_campaigns` to see what went out, while a critical agent reviews the numbers using `get_campaign_performance_details`. They argue over the results. If the open rate is tanking, one agent might suggest changing the design and call `list_email_templates` to see what else is available. They negotiate a solution based on actual API responses before handing you a recommendation.

Subscriber List Audits

You can assign a dedicated compliance agent to monitor your audience health using `list_marketing_address_lists`. It maps out your active segments and checks for anomalies. When a discrepancy appears, a secondary agent jumps in with `list_address_list_subscribers` to inspect the actual contacts. They can even zero in on specific individuals by triggering `search_marketing_subscribers` and debating whether a segment needs cleaning.

Account Limit Monitoring

Before launching a massive sequence, your technical agent runs `get_ecomail_account_metadata`. It checks your account limits and warns the marketing agent if the proposed volume exceeds your capacity. The squad then executes a `quick_marketing_volume_audit` to look at recent activity. If the agents agree that the system is clear, they approve the plan. The entire deliberation relies on live system constraints.

Setup guide

Set up Ecomail 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 Ecomail 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="Ecomail_assistant",
    model_client=OpenAIChatCompletionClient(model="gpt-4o"),
    tools=tools,
)

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

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

Initialize your HTTP transport with `StreamableHttpServerParams` and fetch the tools via `mcp_server_tools`. Pass that directly to your `AssistantAgent` constructor.

Absolutely. One agent can pull the metrics while another critiques the conversion rates. They use the raw data to argue over the best next steps.

An agent uses the search tools to find specific contacts. If the result is ambiguous, it might ask another agent to verify the user profile before taking action.

No. You can give the tools to a single executor agent. The other conversational agents will simply ask the executor to pull the data they need.

Profile histories and campaign metrics are processed in an ephemeral, isolated container. The server handles the authentication token securely, executes the read operation, and shuts down without persisting any of your marketing data to disk.

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