How to Use the Emma MCP in AutoGen

Q: How do I register the Emma MCP server in AutoGen?

Install autogen-extmcp and use mcpservertools with your Vinkius HTTP URL. Pass the resulting tools list to your AssistantAgent constructor to give them access to Emma.

Build multi-agent AutoGen conversations that debate and refine your Emma email marketing campaigns using this MCP server.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Emma MCP to AutoGen

Create your Vinkius account to connect Emma 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 Emma with AutoGen

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Consensus-Driven Group Management

AutoGen lets you set up specialized agents that debate campaign strategy before executing actions. For example, a marketing agent might propose creating a new list using `create_group`, while a compliance agent checks the parameters against `list_fields` to ensure data standards are met. This collaborative workflow prevents accidental list pollution. The agents must reach a consensus on the target audience before calling `list_members`, ensuring your Emma campaigns are highly targeted and compliant with internal rules.

Collaborative Mailing Auditing with AutoGen

When analyzing campaign performance, one AutoGen agent can fetch raw data using `get_mailing_stats` while another agent critiques the copy based on past results from `list_mailings`. They debate which elements drove high open rates and summarize their findings. This multi-perspective analysis gives you a deeper understanding of your email performance. Instead of just looking at raw numbers, the agents negotiate an optimization plan based on historical data retrieved directly from the Emma API.

Safe Automation and Webhook Management

Managing active triggers can be risky, but this MCP server mitigates this by assigning a security agent to audit active webhooks. Before modifying any triggers, the agent runs `list_webhooks` and `list_automations` to map out potential side effects. If the proposed changes risk breaking existing flows, the security agent blocks the action. This guardrail is vital when handling potentially destructive tools like `delete_group`, protecting your active customer segments from accidental removal.

Setup guide

Set up Emma 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 Emma 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="Emma_assistant",
    model_client=OpenAIChatCompletionClient(model="gpt-4o"),
    tools=tools,
)

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

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

Install autogen-ext[mcp] and use mcp_server_tools with your Vinkius HTTP URL. Pass the resulting tools list to your AssistantAgent constructor to give them access to Emma.

Yes. You can set up one AutoGen agent to identify empty groups using list_groups and another to safely execute delete_group after confirming no active members remain.

The framework uses conversation loops where agents debate performance metrics from get_mailing_stats until they reach a consensus on the best optimization strategy.

Yes. AutoGen handles the schema conversion and execution of tools like list_members asynchronously, allowing multiple agents to query the Emma API without blocking the conversation.

All communication with Emma occurs through a secure, single-token Vinkius connection. Subscriber emails and custom fields accessed via get_member are kept strictly in-memory within ephemeral sandbox containers.

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