How to Use the Kajabi MCP in OpenAI Agents SDK

Q: How do I connect Kajabi to the OpenAI Agents SDK?

Install the openai-agents package via pip. Create an MCPServerStreamableHttp instance using your Vinkius endpoint token. Pass that MCP Server directly to the mcpservers array in your Agent constructor.

Q: Can the OpenAI Agents SDK manage Kajabi tags automatically?

Yes. Your agent uses listtags to map available labels, then calls addtagtocontact. Built-in guardrails ensure the agent only applies tags you explicitly authorize in your Python code.

Q: Does the OpenAI Agents SDK support multiple Kajabi sites?

You pass a specific siteid to tools like listcustomers and listorders. The agent isolates its queries to that exact site, preventing data crossover when you manage several creator properties.

Q: How do I cache tool lists for better performance?

Set cacheToolsList=True when initializing the server connection. This stops the agent from refetching the sixteen available operations on every single turn.

Build production-grade creator workflows using the OpenAI Agents SDK to read course data via 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 Kajabi MCP to OpenAI Agents SDK

Create your Vinkius account to connect Kajabi 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 Kajabi with OpenAI Agents SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

OpenAI Agents SDK Handoffs

The `list_contacts` and `get_contact_details` tools pull specific user records directly into your agent state. You build an initial triage agent that reads customer data and evaluates their current product access. Once the triage agent identifies a missing course, it hands off to a specialized marketing agent. That second agent triggers `add_tag_to_contact` to update the user's segmentation profile, all while the OpenAI dashboard traces every single step.

Guardrailed Contact Tagging

The `remove_tag_from_contact` tool strips outdated labels from your user base. You define strict guardrails in Python to ensure your agent only touches accounts meeting specific criteria. If an agent tries to modify a record without checking `list_tags` first, the system blocks the action. You deploy this MCP Server knowing your automated workflows won't accidentally wipe out your entire marketing segmentation strategy.

Course & Offer Audits

Tools like `list_courses`, `list_offers`, and `get_course_details` extract your entire product catalog into context. Your agent cross-references active offers against actual purchase records via `list_purchases`. You write a script that runs every night to find discrepancies between what customers bought and what they can access. The agent flags these edge cases so you can fix them before support tickets pile up.

Setup guide

Set up Kajabi 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 Kajabi tools at runtime.
3

Create your Agent

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

Run the agent

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

Install the `openai-agents` package via pip. Create an `MCPServerStreamableHttp` instance using your Vinkius endpoint token. Pass that MCP Server directly to the `mcp_servers` array in your Agent constructor.

Yes. Your agent uses `list_tags` to map available labels, then calls `add_tag_to_contact`. Built-in guardrails ensure the agent only applies tags you explicitly authorize in your Python code.

You pass a specific `site_id` to tools like `list_customers` and `list_orders`. The agent isolates its queries to that exact site, preventing data crossover when you manage several creator properties.

Set `cacheToolsList=True` when initializing the server connection. This stops the agent from refetching the sixteen available operations on every single turn.

The Vinkius V8 Isolate Sandbox processes names and emails from `get_contact_details` entirely in memory. We destroy the container the second your script finishes running. Nothing touches a persistent disk.

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