How to Use the Flotiq MCP in Pydantic AI

Q: How does Pydantic AI handle Flotiq schema changes?

Your agent runs getcontenttypeschema to fetch the current Flotiq rules. Pydantic AI uses this data to validate incoming and outgoing payloads, raising a validation error if the CMS schema does not match your code.

Q: Can I search Flotiq content using Pydantic AI?

Yes, your agent uses searchglobalcontent and listcontentobjects to find records in Flotiq. Pydantic AI parses the search results into typed Python models, making it easy to use the data in your downstream code.

Q: How do I check my API quota before running batch updates?

You call gettenantlimits to retrieve your active plan thresholds. This allows your agent to calculate how many API requests it can safely make before hitting rate limits.

Force your Pydantic AI agents to validate Flotiq content schemas and media assets at runtime using 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 Flotiq MCP to Pydantic AI

Create your Vinkius account to connect Flotiq 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 Flotiq with Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Strict runtime validation with Pydantic AI

You use `get_content_type_schema` and `list_content_objects` to pull Flotiq's structural rules directly into your Pydantic AI model-agnostic agent. This MCP toolset validates every CMS response against your Pydantic models at runtime, failing loudly if there is a mismatch. You completely eliminate silent data corruption or hallucinated fields in your frontend. If a content editor changes a schema in the CMS, your agent catches the drift instantly. It refuses to write invalid payloads, protecting your production database from schema conflicts.

Type-safe content creation and patching

The `create_cms_object` and `patch_cms_object` tools allow your Pydantic AI agent to mutate CMS data safely. The agent converts raw JSON payloads into validated Python objects before writing them to Flotiq. This ensures that every attribute, string, and number matches your database requirements. By enforcing strict type safety, you can let agents run autonomously on your content pipeline. They write updates, patch existing records, and handle errors without crashing your production build.

Automated workspace cleanup and asset audits

You deploy `list_all_content_types` and `wipe_cms_object` to audit your Flotiq workspace and delete deprecated schemas. The agent inspects your active type vectors and identifies unused data models. It then removes the obsolete nodes to keep your headless CMS clean. Because Pydantic AI enforces strict validation, you can build custom guardrails around destructive tools. The agent will only execute a deletion if the target object matches a specific, validated state schema.

Setup guide

Set up Flotiq 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": {
        "flotiq-mcp": {
            "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
        }
    }
})

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

result = await agent.run("List recent Flotiq 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 Flotiq. 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 Flotiq 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 Flotiq MCP in Pydantic AI

Your agent runs `get_content_type_schema` to fetch the current Flotiq rules. Pydantic AI uses this data to validate incoming and outgoing payloads, raising a validation error if the CMS schema does not match your code.

Yes, your agent uses `search_global_content` and `list_content_objects` to find records in Flotiq. Pydantic AI parses the search results into typed Python models, making it easy to use the data in your downstream code.

Yes, the server connects via Streamable HTTP and SSE transports. Your Pydantic AI agent can stream large datasets, like those returned by `list_media_assets`, without blocking your main application loop.

You call `get_tenant_limits` to retrieve your active plan thresholds. This allows your agent to calculate how many API requests it can safely make before hitting rate limits.

Your Flotiq schemas, content objects, and API keys are processed entirely within Vinkius's secure, ephemeral MCP environment. No data is stored, cached, or logged, ensuring your Pydantic AI content models remain completely private.

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