How to Use the TYPO3 CMS MCP in OpenAI Agents SDK

Q: How can I use TYPO3 CMS with the OpenAI Agents SDK?

You expose the typo3-cms-mcp server to your agent. Your agent then sees the available tools, like createcmsentity. You can write specific workflows that call these tools directly within your production system.

Q: Can my agents check connectivity to TYPO3 CMS using OpenAI Agents SDK?

Yep. Use the pingrestapi tool. Your agent runs this against the endpoint, verifying that everything is connected and ready before trying any write operations. It's a quick health check.

Q: Is it safe for my agents to update TYPO3 CMS using OpenAI Agents SDK?

Updates are handled by updatecmsentity, which takes the entity name, record ID, and JSON updates. Always wrap calls in your agent's guardrails; since this is production code, you don't want accidental changes.

Q: If I need to read a specific TYPO3 CMS page, what tool should I use with OpenAI Agents SDK?

Use getsinglerecord if you know the exact ID. Alternatively, pass an ID or canonical path to getrenderedpage for a structured view of the full content.

Manage TYPO3 content using OpenAI Agents SDK.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect TYPO3 CMS MCP to OpenAI Agents SDK

Create your Vinkius account to connect TYPO3 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 TYPO3 CMS with OpenAI Agents SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Build Production Content Workflows with MCP Server

Need to build a new page or update an existing record? Use `create_cms_entity` and `update_cms_entity`. Your agent can take the entity name and data as JSON, making content creation reliable for production deployments. Don't just read data; change it. The `delete_cms_entity` tool lets your agent permanently remove a TYPO3 record when necessary. Because this action is irreversible, you'll need to bake careful guardrails into your OpenAI Agents SDK workflow.

Audit and Retrieve Page Structures

Getting the full picture of a page is easy with `get_rendered_page`. You just pass in a numeric ID or canonical path, and your agent gets a structured representation of that content. You can also map out the whole site using `get_navigation_tree`, which retrieves the hierarchical menu starting from any given page. This is crucial for agents designing new sections within TYPO3 CMS.

Analyze and List Backend Records

Want to see all records belonging to a specific content type? The `list_backend_records` tool handles this. You provide the entity name and optional query parameters, and your agent gets back a list of matching TYPO3 CMS data. If you're checking system-level settings, `list_typoscript_globals` pulls all global TypoScript constants. This lets your agents audit configurations before deploying changes.

Setup guide

Set up TYPO3 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 TYPO3 CMS tools at runtime.
3

Create your Agent

Pass the MCP to Agent(mcp_servers=[server]). The agent receives TYPO3 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 TYPO3 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="TYPO3 CMS Agent",
            instructions="You have access to TYPO3 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 TYPO3 CMS. 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 TYPO3 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 TYPO3 CMS MCP in OpenAI Agents SDK

You expose the `typo3-cms-mcp` server to your agent. Your agent then sees the available tools, like `create_cms_entity`. You can write specific workflows that call these tools directly within your production system.

Yep. Use the `ping_rest_api` tool. Your agent runs this against the endpoint, verifying that everything is connected and ready before trying any write operations. It's a quick health check.

The server touches general backend records and content elements, including the ability to list global TypoScript settings via `list_typoscript_globals`. This covers configuration data.

Updates are handled by `update_cms_entity`, which takes the entity name, record ID, and JSON updates. Always wrap calls in your agent's guardrails; since this is production code, you don't want accidental changes.

Use `get_single_record` if you know the exact ID. Alternatively, pass an ID or canonical path to `get_rendered_page` for a structured view of the full content.

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