How to Use the Builder MCP in Pydantic AI

Q: How do I connect Pydantic AI to the Builder MCP Server?

Install pydantic-ai-slimmcp and use the MCPToolset class pointing to your Vinkius endpoint. Pass this toolset directly to your Agent constructor to give your typed agents full access to the CMS tools.

Build type-safe CMS integrations using Pydantic AI to validate Builder models at runtime.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Builder MCP to Pydantic AI

Create your Vinkius account to connect Builder 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 Builder with Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Strict validation for Builder schemas

`get_model_schema` pulls the exact JSON schema of your Builder models directly into your Pydantic AI agent. The framework validates every incoming field against your Python types, throwing immediate errors if there is a mismatch. This strict runtime check prevents corrupted data from hitting your production CMS. If an LLM attempts to output an invalid field type, Pydantic AI halts the execution before any write happens.

Type-safe block updates via MCP Server

`update_visual_block` modifies your live layouts only after Pydantic AI validates the block's structure. The agent maps the layout payload against your defined Pydantic models to ensure complete structural integrity. If you need to remove old layouts, `wipe_visual_block` handles the deletion safely. Your agent confirms the target block ID matches your strict type constraints before executing the destructive action.

Guaranteed content parsing

`get_single_content` retrieves a specific layout document via MCP and parses it directly into a typed Python object. Pydantic AI guarantees that your agent never works with unpredictable or dirty JSON from your headless CMS. When querying multiple entries with `list_model_content`, the framework filters out any malformed payloads. You get clean, typed data structures that your application can safely render.

Setup guide

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

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

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

Install pydantic-ai-slim[mcp] and use the MCPToolset class pointing to your Vinkius endpoint. Pass this toolset directly to your Agent constructor to give your typed agents full access to the CMS tools.

The runtime validation will fail loudly with a ValidationError. This prevents your pipeline from processing corrupted data or writing bad payloads back to your models via create_visual_block.

Yes, Pydantic AI uses the modern MCP toolset which supports both Streamable HTTP and SSE transports. This ensures fast, reliable communication when fetching large media metadata using get_media_file.

Yes, Pydantic AI is model-agnostic. You can run your Builder workflows using local models or other API providers while maintaining strict type-safety across tools like search_active_models.

Vinkius processes all requests inside an ephemeral, zero-trust sandbox. Your Builder API keys, visual blocks, and model structures are never stored or logged, ensuring strict compliance and data isolation.

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