How to Use the Customer.io MCP in AutoGen

Q: How do I load Customer.io tools into AutoGen?

Install the autogen-extmcp package. Use mcpservertools with your Vinkius URL, and the adapter will automatically convert the marketing API schemas for your AssistantAgent.

Q: Does the adapter handle the complex engagement metrics schema?

The McpToolAdapter handles all schema conversions natively. Your agents see the exact parameters required for fetching sent, opened, clicked, and converted counts without manual mapping.

Build debating marketing teams in AutoGen. Let autonomous agents analyze Customer.io data and agree on campaign updates.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Customer.io MCP to AutoGen

Create your Vinkius account to connect Customer.io 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 Customer.io with AutoGen

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Multi-agent MCP Server analysis

AutoGen thrives on competing perspectives. You can assign a data-analyst agent to pull KPIs via `get_engagement_summary` while a strategist agent reviews the numbers and suggests adjustments. The agents talk to each other before touching your workspace. If one proposes an aggressive broadcast schedule based on `list_broadcast_messages`, a compliance agent can challenge the frequency based on audience fatigue rules.

Consensus-driven profile updates

Modifying user records requires deliberation. A support agent might want to flag an account, but it must convince the lead agent to actually execute `identify_customer` and mutate the database. Finding the right user happens through conversation. One agent runs `search_customers_by_email`, passes the identifier to another agent to run `get_customer_details`, and together they verify the device tokens match the expected state.

Debate campaign triggers

Designing automation paths is no longer a single-prompt task. Your agents pull existing workflows using `list_automated_campaigns` and argue over which trigger types perform best. Segment targeting gets the same treatment. The team checks dynamic lists via `list_customer_segments` and debates whether the membership counts justify launching a new sequence from `list_newsletters`.

Setup guide

Set up Customer.io 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 Customer.io 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="Customer.io_assistant",
    model_client=OpenAIChatCompletionClient(model="gpt-4o"),
    tools=tools,
)

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

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

Install the `autogen-ext[mcp]` package. Use `mcp_server_tools` with your Vinkius URL, and the adapter will automatically convert the marketing API schemas for your AssistantAgent.

That is exactly how the framework operates. One agent fetches delivery metrics, another critiques the open rates, and they negotiate a conclusion before returning an answer.

You decide during setup. You can restrict the profile identification tool to a specific execution agent, forcing the planning agents to hand off the final action.

The `McpToolAdapter` handles all schema conversions natively. Your agents see the exact parameters required for fetching sent, opened, clicked, and converted counts without manual mapping.

Your endpoint token is the only key to your workspace. The managed MCP infrastructure routes your requests for scheduling metadata and audience lists through a secure, stateless proxy that forgets the data instantly.

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