How to Use the Klaviyo (Marketing Automation) MCP in OpenAI Agents SDK

Q: How do I connect the Klaviyo (Marketing Automation) MCP to OpenAI Agents SDK?

Install openai-agents. Create an MCPServerStreamableHttp instance with your server URL. Pass it to your agent via mcpservers=server and set cacheToolsList=True to speed up tool discovery.

Q: Can OpenAI Agents SDK create new Klaviyo profiles?

Yes. The agent uses the createprofile tool. It requires an email address and accepts optional first and last names for personalization.

Q: How do I list my customer segments?

Call listaudiencesegments. This pulls the dynamically updating cohorts based on behavioral data, giving your agent the current state of your customer base.

Connect Klaviyo to OpenAI Agents SDK to automate list management and audit marketing flows in production.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Klaviyo (Marketing Automation) MCP to OpenAI Agents SDK

Create your Vinkius account to connect Klaviyo (Marketing Automation) 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 Klaviyo (Marketing Automation) with OpenAI Agents SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Manage segments via MCP Server

Your agent needs to move users around based on behavior. This MCP Server exposes `list_audience_segments` so the model can read your dynamic cohorts. It sees who falls into churn risk or high-value buckets. Once the agent decides a user needs a specific intervention, it calls `add_profiles_to_list`. OpenAI's built-in guardrails ensure the agent doesn't dump the wrong IDs into your VIP lists.

Inspect active campaigns

Marketing teams often lose track of what is actually sending right now. Give your agent access to this MCP Server and it pulls the current broadcast schedule using `list_email_campaigns`. If a broadcast looks suspicious, the agent triggers `get_campaign_details`. It pulls the exact message content and target audience IDs. You get full visibility into the agent's logic through the OpenAI dashboard.

Debug lifecycle triggers

Automated sequences break when triggers overlap. You can map out your entire setup using `list_automation_flows`. The agent grabs every active welcome series and abandoned cart sequence. Then it digs deeper with `get_flow_details`. It reads the entry conditions and action steps. If a delay is set wrong, your agent flags it before it ruins a launch.

Setup guide

Set up Klaviyo (Marketing Automation) 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 Klaviyo (Marketing Automation) tools at runtime.
3

Create your Agent

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

Run the agent

Call Runner.run(agent, prompt) to execute. The agent invokes the appropriate Klaviyo (Marketing Automation) 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="Klaviyo (Marketing Automation) Agent",
            instructions="You have access to Klaviyo (Marketing Automation) 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 Klaviyo. 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 Klaviyo (Marketing Automation) 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 Klaviyo (Marketing Automation) MCP in OpenAI Agents SDK

Install `openai-agents`. Create an `MCPServerStreamableHttp` instance with your server URL. Pass it to your agent via `mcp_servers=[server]` and set `cacheToolsList=True` to speed up tool discovery.

Yes. The agent uses the `create_profile` tool. It requires an email address and accepts optional first and last names for personalization.

It does. You define the rules for list modification. If the agent tries to run `add_profiles_to_list` outside those constraints, the SDK blocks the execution.

Call `list_audience_segments`. This pulls the dynamically updating cohorts based on behavioral data, giving your agent the current state of your customer base.

Vinkius runs this MCP Server in an ephemeral V8 Isolate sandbox. When your agent calls `get_profile`, the phone numbers, addresses, and predictive CLV scores pass directly to your client. We do not log or store the payload.

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