How to Use the TYPO3 CMS MCP in Pydantic AI

Q: Can I use Pydantic AI for content creation and updates in TYPO3 CMS?

Yes. You can use createcmsentity to build new records, and updatecmsentity to modify existing ones. The type safety ensures that your JSON payload structure is correct before sending it to the server.

Q: If I need to audit TYPO3 CMS configurations, what tools should I use with Pydantic AI?

Check system settings using listtyposcriptglobals for constants. You can also run getinitialboot to understand the core root page schema and global config.

Validate TYPO3 CMS changes with Pydantic AI.

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 Pydantic AI

Create your Vinkius account to connect TYPO3 CMS to Pydantic AI 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 Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Type-Safe Content Updates via MCP Server

Need to make sure an update is correct? Use `update_cms_entity`. You provide the entity name, record ID, and JSON updates. Because your agent uses Pydantic AI, if the API returns bad data—or if the required fields are missing—the agent fails loudly with a validation error. This prevents silent corruption when changing content elements or Extbase entities within TYPO3 CMS.

Systematic Data Retrieval and Listing

To get a full list of records, use `list_backend_records`. Pass the entity name and parameters. Pydantic AI guarantees that the resulting data structure matches your expected schema, which is vital when processing large sets of TYPO3 CMS content. For single-record lookups, `get_single_record` retrieves exactly what you asked for, validated against a defined model.

Site Structure Mapping with MCP Server

Mapping out the site is critical. Use `get_navigation_tree` to get the full hierarchical menu structure starting from a page. The structured output validates perfectly against your Pydantic models. If you need to view all global TypoScript settings, `list_typoscript_globals` pulls those constants and formats them so your agent can ingest them without guesswork.

Setup guide

Set up TYPO3 CMS MCP in Pydantic AI

Prerequisites

Python 3.10+ installed
pydantic-ai-slim[fastmcp] package
Active Vinkius subscription with a valid endpoint token

1

Install Pydantic AI with FastMCP
Run pip install "pydantic-ai-slim[fastmcp]". The FastMCP toolset replaces the deprecated MCPServerHTTP class with full protocol support.
2

Configure the FastMCPToolset
Pass a JSON-style config dict to FastMCPToolset with your Vinkius URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. Supports Streamable HTTP, SSE, and Stdio transports.
3

Create and run your agent
Pass the toolset to Agent(toolsets=[toolset]) and call agent.run(). Swap openai:gpt-4o for any supported model — Anthropic, Google, Mistral, or Groq.

agent.py

from pydantic_ai import Agent
from pydantic_ai.toolsets.fastmcp import FastMCPToolset

toolset = FastMCPToolset({
    "mcpServers": {
        "typo3-cms-mcp": {
            "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
        }
    }
})

agent = Agent(
    "openai:gpt-4o",
    toolsets=[toolset],
    system_prompt="You have access to TYPO3 CMS tools.",
)

result = await agent.run("List recent TYPO3 CMS transactions")
print(result.output)

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 Pydantic AI

Pydantic validates every MCP response at runtime. If the underlying API call fails to return data that matches your defined schema, your agent doesn't continue; it throws a clear validation error instead.

Yes. You can use `create_cms_entity` to build new records, and `update_cms_entity` to modify existing ones. The type safety ensures that your JSON payload structure is correct before sending it to the server.

You can model anything from global TypoScript settings (via `list_typoscript_globals`) to complex page structures retrieved by `get_rendered_page`. The framework adapts to the source data.

Check system settings using `list_typoscript_globals` for constants. You can also run `get_initial_boot` to understand the core root page schema and global config.

This server touches general backend records and content elements. Since your agent validates every piece of retrieved data, you'll know exactly what type of record or configuration field was accessed via `list_backend_records`.

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