How to Use the Customer.io MCP in OpenAI Agents SDK

Q: How do I initialize the Customer.io tools inside OpenAI Agents SDK?

Install the SDK and use MCPServerStreamableHttp to connect to the Vinkius MCP endpoint. Pass the server instance directly into your Agent constructor's mcpservers list. The SDK automatically discovers all ten tools, making them instantly available to your model.

Q: Can OpenAI Agents SDK automatically update user traits in Customer.io?

Yes, the agent uses identifycustomer to write custom attributes and device tokens to your workspace. You define safety guardrails in your Python code to ensure the agent only writes validated schemas to your user profiles.

Run production-ready customer communication loops by connecting OpenAI Agents SDK directly to your Customer.io workspace.

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 OpenAI Agents SDK

Create your Vinkius account to connect Customer.io to OpenAI Agents SDK 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 OpenAI Agents SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Route users dynamically using OpenAI Agents SDK

This MCP Server exposes `identify_customer` and `list_customer_segments` to let your OpenAI agents update user profiles and evaluate segment memberships on the fly. When a customer takes an action in your app, the SDK routes the event to a specialized agent that immediately syncs their profile traits. You get complete visibility through the OpenAI tracing dashboard. If an agent attempts to modify a restricted attribute, the SDK's built-in guardrails block the call before it hits the API, keeping your production user database clean.

Track campaign metrics directly in OpenAI Agents SDK

The `get_campaign_performance` and `get_engagement_summary` tools feed live email, push, and SMS performance data straight to your analytics agents. Instead of exporting CSVs, your agent reads open rates and conversions to adjust follow-up sequences automatically. The SDK handles agent-to-agent handoffs, passing performance summaries from a reporting agent to a copywriter agent. You configure this with a simple context manager in Python, letting specialized models focus on their exact tasks.

Query message history for automated workflows

This integration uses `list_automated_campaigns` and `list_broadcast_messages` to let your agent inspect active marketing flows and schedule targeted broadcasts. The agent queries your live workspace setup to verify which campaigns are active before triggering new events. By setting `cacheToolsList=True` during initialization, your agents discover these tools instantly without making redundant network calls. It keeps your latency low while giving your LLM full access to your email marketing setup.

Setup guide

Set up Customer.io MCP in OpenAI Agents SDK

Prerequisites

Python 3.10+ installed
openai-agents package (pip install openai-agents)
Active Vinkius subscription with a valid endpoint token

1

Install the SDK

Run pip install openai-agents to install the OpenAI Agents SDK. The MCP integration is built-in — no extra dependencies needed.
2

Connect via SSE transport

Use MCPServerSse with your Vinkius endpoint URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. The SDK auto-discovers all Customer.io tools at runtime.
3

Create your Agent

Pass the MCP to Agent(mcp_servers=[server]). The agent receives Customer.io tools as native definitions — JSON schemas resolve automatically.
4

Run the agent

Call Runner.run(agent, prompt) to execute. The agent invokes the appropriate Customer.io tools and returns structured results. Copy the full example on the right to get started.

agent.py

import asyncio
from agents import Agent, Runner
from agents.mcp import MCPServerSse

async def main():
    async with MCPServerSse(
        url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    ) as server:
        agent = Agent(
            name="Customer.io Agent",
            instructions="You have access to Customer.io tools.",
            mcp_servers=[server],
        )
        result = await Runner.run(agent, "List recent transactions")
        print(result.final_output)

asyncio.run(main())

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 OpenAI Agents SDK

Install the SDK and use `MCPServerStreamableHttp` to connect to the Vinkius MCP endpoint. Pass the server instance directly into your Agent constructor's `mcp_servers` list. The SDK automatically discovers all ten tools, making them instantly available to your model.

Yes, the agent uses `identify_customer` to write custom attributes and device tokens to your workspace. You define safety guardrails in your Python code to ensure the agent only writes validated schemas to your user profiles.

The SDK manages tool execution retries, but you should also set up your agent handoffs to throttle high-volume requests. If a tool like `get_customer_details` hits a rate limit, the error traces directly to your OpenAI dashboard for quick debugging.

You control tool exposure at the SDK level by filtering the server tools list before passing it to the Agent constructor. This prevents a support agent from calling `list_broadcast_messages` while still letting it look up profiles.

The server processes email addresses and device tokens within an isolated V8 sandbox hosted on Vinkius. No customer data is stored on our servers, and all API calls to your workspace are encrypted in transit.

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