How to Use the Kontent.ai (Enterprise Headless CMS) MCP in OpenAI Agents SDK

Q: Can my agent publish content live using this MCP Server?

Yes, the agent can publish live variants. It uses upsertlanguagevariant to write the draft content first, then calls publishvariant to push that draft to the live delivery API. This lets you automate your entire publishing pipeline safely.

Run production-grade content workflows in the OpenAI Agents SDK using safe, traced calls to your headless CMS.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Kontent.ai (Enterprise Headless CMS) MCP to OpenAI Agents SDK

Create your Vinkius account to connect Kontent.ai (Enterprise Headless CMS) 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 Kontent.ai (Enterprise Headless CMS) with OpenAI Agents SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Automate localization with OpenAI Agents SDK

The `upsert_language_variant` tool lets your agent update draft text for specific target locales directly within your CMS workspace. Instead of copying and pasting translations, the agent writes directly to the correct language field. You can build a specialized translation agent that handles the initial draft, then hand off the execution to a publishing agent. This second agent uses `publish_variant` to send the translated content directly to production delivery APIs.

Audit schema and query content structures

The `get_content_type` tool allows your agent to read the exact structure of your CMS content models at runtime. Your agent checks field rules and data types before trying to create new entries, preventing bad API requests. Running `list_content_types` gives the agent a map of all available schemas in your project. It uses this map to decide which fields to populate, making sure your automated content updates always match your actual database schema.

Manage top-level containers safely

Using `upsert_item` creates or updates a core content item container without touching the actual localized language fields. This separates the structural item setup from the actual text draft, keeping your content tree clean. Monitoring these container creations happens directly in your OpenAI dashboard. If an agent tries to modify a container it shouldn't touch, the SDK's built-in guardrails block the action before it hits your production CMS.

Setup guide

Set up Kontent.ai (Enterprise Headless CMS) 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 Kontent.ai (Enterprise Headless CMS) tools at runtime.
3

Create your Agent

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

Run the agent

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

Install the SDK with pip install openai-agents and initialize the server using MCPServerStreamableHttp. Pass the server instance inside the mcp_servers list when instantiating your Agent. Set cacheToolsList=True to speed up tool discovery during agent startup.

Yes, the agent can publish live variants. It uses upsert_language_variant to write the draft content first, then calls publish_variant to push that draft to the live delivery API. This lets you automate your entire publishing pipeline safely.

The SDK uses built-in guardrails and tracing to validate agent actions before execution. By first calling get_content_type, the agent verifies the exact structural fields required, preventing invalid schema writes using this MCP integration.

Yes, you can set up agent handoffs. One agent can find assets using list_assets, while a separate publishing agent takes over to run publish_variant when the draft is approved using this custom MCP Server setup.

This MCP Server only handles your specific CMS data types, like content items, language variants, and taxonomy terms. All API traffic runs through a secure, ephemeral V8 isolate sandbox managed by Vinkius, meaning your raw draft text and asset metadata are never stored or used to train public models.

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