TYPO3 MCP: What Is the Model Context Protocol and How Do You Use It?

Ask a chat assistant for a meta description and the real work starts afterwards: copy, open the page in the TYPO3 backend, paste, save. Then the next page. The Model Context Protocol, MCP for short, takes that loop away. Your assistant reads the page tree, drafts pages and uploads files inside TYPO3 itself. It only gets the rights you choose to give it.

Anyone searching for TYPO3 MCP wants two answers. One is a definition. The other matters more: what a connected AI may touch. You will find both below, followed by a six-step setup and a security checklist.

MCP is an open standard for connecting AI applications to the systems where your data lives. With it, an assistant such as Claude, ChatGPT or Cursor can query a database, work with files, or create pages in a CMS like TYPO3.

Since 9 December 2025 the protocol has been hosted by the Agentic AI Foundation, a fund under the Linux Foundation co-founded by Anthropic, Block and OpenAI. It began at Anthropic, which open-sourced MCP on 25 November 2024. The goal was to end one-off integrations, because every new data source needed its own. The latest specification is dated 2026-07-28.

Think of MCP like a USB-C port for AI applications.

Model Context Protocol documentation, modelcontextprotocol.io, accessed 11 September 2026

One port, many devices. The TYPO3 equivalent is one MCP server inside the installation you already run. Any suitable assistant connects to that one server, so no assistant needs an extension of its own.

Start with the server, which exposes data and actions. On a TYPO3 site it runs inside your installation. The host is the AI application you work in, such as Claude Desktop or Visual Studio Code. The host opens one client per server connection, and that client carries the conversation.

Servers offer three kinds of primitive, in the specification's terms:

For TYPO3, tools matter most. They are what changes your site.

Local development usually pipes messages through standard input and output (stdio) on one machine. Across the network, the assistant talks to TYPO3 over HTTP. For that route, the MCP architecture overview recommends OAuth, the common standard for delegated access. Both routes come ready for you in AI Foundation.

Behind the diagram are four hops:

1. An editor types a plain question.
2. The assistant fetches the server's tool list and calls the tool that fits.
3. TYPO3 runs the query as the connected backend user, within that user's rights.
4. The answer returns along the same path.

Without MCP, AI reaches TYPO3 by hand: a chat draft, a person, a paste. TYPO3 never learns where the text came from. The table shows what the Model Context Protocol for TYPO3 changes:

The access row is where TYPO3 AI integration pays off. Your editors already work inside a permission model, and an AI with its own backend user slots straight into it. From then on, you govern it like any other account.

Start with the chores. These four requests show the style: plain language, nothing more.

• "Create a new page under Blog in the draft workspace, using the heading and text from this document."
• "Upload the image from this URL to the blog folder and suggest alt text."
• "Redirect the old product page to the new one with a 301."
• "List the pages in the Products section that have no meta description."

What is available depends on your installation:

More than 100 MCP tools ship with the foundation and the AI extensions combined. Every one of them slots into the installation you already have.

For developers: your own tables, tools and skills

The same MCP server can open your own tables and endpoints to the assistant.

• Your own tables. Discover Extension Tables finds tables in your extensions. Each one you enable gets nine tools for creating, reading, updating and deleting records.
• Custom tools. Point a new tool at a PHP class, a REST endpoint or a webhook, all from one dialog.
• Prompt templates. Clients fetch them through prompts/list and prompts/get, including the built-in add_content_text_block for turning an editor's brief into a text element.
• Skills. Every AI extension ships a Markdown skill file for your assistant, and the Skill Hub imports more.

Bring TYPO3 v12, v13 or v14, PHP 8.2 or later, and Composer. The six steps at a glance:

1. Install AI Foundation: composer require nitsan/ns-t3af. No licence key, no registration.
2. Switch on the MCP server: AI Foundation, then MCP Server, then the Advanced tab.
3. Give the assistant its own user: a backend user reserved for the assistant, with limited rights. Keep your admin account out of it.
4. Connect your assistant: pick Remote (OAuth) on the Connect tab, copy the server URL and approve access in the browser.
5. Try the tools in the Playground: run a single tool against your installation, no client needed.
6. Start with a read-only task: let the assistant read first, then check every change in the backend and on the rendered page.

Our post on TYPO3 MCP setup walks through every step in detail, with screenshots and a final check.

Working locally with the DDEV development environment? AI Foundation connects directly through the TYPO3 command line too. Building extensions with an assistant is covered in our guide to Claude Code and TYPO3.

The screenshots show the AI Foundation interface, captured on t3planet.de. The Connect tab was captured on our demo install.

The MCP server guide in the AI Foundation documentation covers every connection method in detail. For the first steps with someone at your side, book an MCP demo for TYPO3 with Jürgen.

This post is its own example. Claude, Anthropic's AI assistant, reaches our TYPO3 installation on t3planet.de through the AI Foundation MCP server. Here are two moments from the work, one reading and one writing.

Reading: is the topic already taken?

The first task came before any writing. Claude had to find out whether one of our pages already covered the topic. Two calls to the pages_search tool settled it:

1. Pages with "mcp" in the URL: 0 results.
2. Pages with "MCP" in the title: 2 results, our AI Foundation post in English and German.

Two read-only calls turned a hunch into a decision, and nothing on the site changed. This post explains the protocol; the existing one covers the product.

Writing: the page is built hidden

Writing uses the same connection. With the copy approved, Claude builds this page in both languages, title, description and content included, and leaves it hidden. A person on our team decides when it goes live.

The first post we built this way taught us one thing. The database reported a clean save, yet the rendered page had defects. A clean save proves nothing, so every page now gets a browser check in both languages, on desktop and phone. Open every AI-written page in a browser before it goes live. The check fits the review your team already runs.

Pick a mode, and you pick the author. AI Foundation's two MCP modes also decide where your content travels.

• Context mode (default). The assistant's own model writes, and MCP tools place the result in TYPO3. Connect Claude Desktop, for instance, and Anthropic's model is the author. Anything the assistant reads for the task is sent to Anthropic.
• Native mode. The text is generated inside TYPO3 by the providers configured in AI Foundation. Your assistant gives the instruction. Tool results it reads still reach its provider.

After a mode switch, reconnect the client so it gets the new tool descriptions.

Native mode is where multi-LLM in TYPO3 happens: several large language models side by side. Seven platforms are built in, each a dependency in the Packagist listing for version 1.2.2: OpenAI, Anthropic, Google Gemini, Mistral, Azure, OpenRouter and Ollama. Any OpenAI-compatible provider works too. Run Ollama and the model stays on your own infrastructure. On your own API keys, the default, content goes straight from your server to the provider you picked, with T3Planet outside that data path.

Which provider sees which content is among the first questions in any data protection review, as our GDPR check for AI chatbots and AI search shows. With AI Foundation that choice stays yours, and the software fits around it. How far your content travels then differs, depending on the model you choose; with the optional AI Credits, T3Planet is in the data path as well. Our post on the MCP-First AI Foundation for TYPO3 goes deeper into managing providers, prompts and budgets.

An assistant with write access is a colleague with a login. Hold it to the same rules. AI Foundation puts six controls in your hands:

• OAuth 2.1 with PKCE. One backend user per token, an expiry date, and a revoke button for each.
• Scopes. A ceiling on what any client may do, as low as read-only.
• IP allowlist. Requests from outside your approved ranges never reach the server.
• Mutual TLS (mTLS). A signed client certificate can replace the token entirely.
• Workspaces. Drafted pages and content stay drafts until someone with publish rights releases them. Files, redirects and scheduler tasks have no draft state in TYPO3, so grant those rights with care.
• Logs and limits. Per-client tool calls, success rates, errors and quotas, visible in the backend.

Five questions worth asking of any MCP server for TYPO3, ours included:

1. Can you narrow the AI's rights to certain pages and languages?
2. Do writes stop at a draft first?
3. Could you cut off one client right now without affecting the rest?
4. Will you find out afterwards which client called which tool?
5. Do you choose the model, and can you trace your content's route?

Everything in the setup above runs on AI Foundation for TYPO3, T3Planet's open-source AI foundation. Behind it is NITSAN Technologies, a team with more than 15 years of TYPO3 experience, over 3,200 customers and Gold membership in the TYPO3 Association. One backend module holds the MCP server and your AI providers. Add the AI extensions and it carries more than 100 MCP tools. The foundation itself costs nothing.

Browse the AI extensions that build on it in our overview of TYPO3 AI extensions. Then explore AI Foundation for TYPO3, or book an MCP demo for TYPO3 with Jürgen and make the first connection together, on your own use case.