How to Use the 4D MCP in Pydantic AI

Connect your 4D database to Pydantic AI for type-safe, strictly validated database operations.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect 4D MCP to Pydantic AI

Create your Vinkius account to connect 4D 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 4D with Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Validate 4D schemas at runtime via MCP Server

The `get_catalog` tool fetches the exact schema from your backend, allowing Pydantic AI to validate every table definition. Type safety matters when an agent interacts with a production database. If the API returns a DataClass that doesn't match your expected model, the framework fails loudly with a validation error. Silent corruption destroys data integrity. By wrapping your Vinkius endpoint in an MCPToolset, you force the agent to respect the actual structure of your database. Your model-agnostic setup works flawlessly whether you use Claude, Gemini, or a local model to parse the catalog.

Execute strict ORDA queries

The `list_entities` tool queries records by accepting specific $filter and $orderby parameters. Pydantic AI guarantees that the agent formats these ORDA arguments correctly before the request ever leaves your server. The framework catches hallucinated parameters instantly. Fetching a single row requires a valid primary key. When the agent calls `get_entity`, the response gets checked against your runtime models. You know exactly what data shape you are getting back.

Mutate records without hallucinated fields

The `create_entity` tool handles row insertion, but Pydantic AI ensures the JSON payload contains no invented columns. Pushing new rows into a table demands a perfectly formatted string. The agent throws a strict error if it attempts to write outside the defined schema. Modifying data works the exact same way. Calling `update_entity` requires strict adherence to the existing record structure. If an agent needs to drop a row via `delete_entity`, the framework verifies the primary key format before executing the destructive command.

Setup guide

Set up 4D 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": {
        "4d-mcp": {
            "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
        }
    }
})

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

result = await agent.run("List recent 4D 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 4D. 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 4D 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 4D MCP in Pydantic AI

You instantiate an MCPToolset with your Vinkius HTTP endpoint. Pass that toolset array directly to your Agent constructor to expose the database tools.

Yes, every response from the database gets checked against your defined models. The framework throws a strict validation error if the API returns unexpected field names.

The framework is completely model-agnostic. You can generate ORDA syntax using OpenAI, Anthropic, or even local models running on your own hardware.

The unified MCPToolset replaces older transport classes. It handles both Streamable HTTP and SSE connections internally for better reliability.

We run your connection inside an ephemeral V8 Isolate Sandbox that terminates immediately after use. Your ORDA filters, JSON payloads, and primary keys never touch persistent storage. Auth relies entirely on a single endpoint token.

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