How to Use the Klaviyo MCP in OpenAI Agents SDK

Q: How do I initialize the Klaviyo MCP server in the OpenAI Agents SDK?

Initialize an MCPServerStreamableHttp object with your endpoint URL. Pass it into the mcpservers array when constructing your agent. The SDK handles tool discovery automatically.

Q: How do I speed up MCP tool discovery in production?

Set cacheToolsList=True in your server parameters. This prevents the agent from re-asking the API for its tool schema on every single turn.

Connect this Klaviyo MCP Server to your OpenAI Agents SDK production system to trigger flows and track events with built-in guardrails.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Klaviyo MCP to OpenAI Agents SDK

Create your Vinkius account to connect Klaviyo 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 with OpenAI Agents SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Manage Campaigns with OpenAI Agents

The `list_campaigns` and `list_email_templates` tools give your agent direct read access to your outbound marketing assets. You can build a specialized agent that reviews past performance before drafting new copy. Setting `cacheToolsList=True` keeps the agent responsive when fetching these lists repeatedly. Handoffs change the workflow. One agent pulls historical data using `list_metrics`, then passes the context to a secondary agent tasked with generating the actual email body. You get full visibility into the execution chain through the OpenAI dashboard.

Map Customer Events via MCP Server

Pushing real-time actions requires the `track_event` tool to log what users do inside your application. Your agent captures a checkout or a button click, formats the payload, and fires it off to the growth engine. This skips the manual API integration work entirely. Guardrails prevent garbage data from entering your marketing queues. You define strict parameters for what constitutes a valid event before the agent ever hits the endpoint. Bad payloads get rejected locally instead of polluting your customer records.

Read Audience Segments Automatically

Fetching current audience data happens through the `list_segments` and `list_marketing_lists` tools. Agents read these structures to understand where a specific user belongs. If someone asks to be removed from promotional blasts, the system knows exactly which lists to check. We use `get_profile` to verify the current state of a subscriber. If they are missing, the agent calls `create_profile` to register them instantly. Everything runs through the standard `MCPServerStreamableHttp` connection without writing custom wrapper functions.

Setup guide

Set up Klaviyo 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 tools at runtime.
3

Create your Agent

Pass the MCP to Agent(mcp_servers=[server]). The agent receives Klaviyo 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 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 Agent",
            instructions="You have access to Klaviyo 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 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 MCP in OpenAI Agents SDK

Initialize an `MCPServerStreamableHttp` object with your endpoint URL. Pass it into the `mcp_servers` array when constructing your agent. The SDK handles tool discovery automatically.

Yes. You write local validation rules that check the payload before it reaches the network. If an agent tries to fire a tracking event without a required email address, the guardrail stops execution.

It does. One agent can execute an automated flow to gather context and then hand off control to a specialized support agent. Tracing in the dashboard shows exactly where the transition occurred.

Set `cacheToolsList=True` in your server parameters. This prevents the agent from re-asking the API for its tool schema on every single turn.

The agent processes email addresses and phone numbers in memory for the duration of the run. Vinkius runs the integration in an ephemeral V8 Isolate Sandbox, meaning the connection drops and memory clears the second the task finishes. Zero data rests on intermediate disks.

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