How do I find which tables are available?

Use the `get_catalog` tool. It will return a list of all DataClasses (tables) exposed through the REST API in your 4D Server.

Can I filter data based on specific conditions?

Yes. Use the `list_entities` tool and provide an ORDA-style filter string in the `$filter` parameter (e.g., "status = 'active' AND price > 100").

Does this support creating new records?

Absolutely. Use the `create_entity` tool by providing the DataClass name and a JSON string containing the field data for the new record.

4D MCP Server for Pydantic AI 6 tools — connect in under 2 minutes

Name: 4D
Availability: InStock
Author: Vinkius

ai.pydantic.dev/mcp

Built by Vinkius GDPR 6 Tools SDK

Pydantic AI brings type-safe agent development to Python with first-class MCP support. Connect 4D through Vinkius and every tool is automatically validated against Pydantic schemas. catch errors at build time, not in production.

Get MCP Server for AI Agents

ASK AI ABOUT THIS MCP SERVER

Open in ChatGPT Open in Claude Open in Perplexity

Vinkius supports streamable HTTP and SSE.

python

import asyncio
from pydantic_ai import Agent
from pydantic_ai.mcp import MCPServerHTTP

async def main():
    # Your Vinkius token. get it at cloud.vinkius.com
    server = MCPServerHTTP(url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp")

    agent = Agent(
        model="openai:gpt-4o",
        mcp_servers=[server],
        system_prompt=(
            "You are an assistant with access to 4D "
            "(6 tools)."
        ),
    )

    result = await agent.run(
        "What tools are available in 4D?"
    )
    print(result.data)

asyncio.run(main())

Fully ManagedVinkius Servers

60%Token savings

High SecurityEnterprise-grade

IAMAccess control

EU AI ActCompliant

DLPData protection

V8 IsolateSandboxed

Ed25519Audit chain

<40msKill switch

Stream every event to Splunk, Datadog, or your own webhook in real-time

* Every MCP server runs on Vinkius-managed infrastructure inside AWS - a purpose-built runtime with per-request V8 isolates, Ed25519 signed audit chains, and sub-40ms cold starts optimized for native MCP execution. See our infrastructure

About 4D MCP Server

Bridge your 4D Server with the world of AI Agents through the power of ORDA (Object Relational Data Architecture). This integration transforms your 4D database into an intelligent, queryable knowledge base, allowing your AI agent to explore structures and manage records through natural conversation. No more manual REST calls; your agent can now audit catalogs, run complex entity queries, and perform high-speed CRUD operations, ensuring your 4D data is always accessible and actionable within your AI workflows.

Pydantic AI validates every 4D tool response against typed schemas, catching data inconsistencies at build time. Connect 6 tools through Vinkius and switch between OpenAI, Anthropic, or Gemini without changing your integration code. full type safety, structured output guarantees, and dependency injection for testable agents.

What you can do

Database Exploration — Retrieve the full catalog of DataClasses (tables) and their attribute definitions (fields) to map your data structure.
Advanced Querying — Perform complex data lookups using filters, ordering, and expansion of related entities with ORDA syntax.
CRUD Operations — Create, read, update, and delete records across any exposed DataClass in your 4D environment.
Metadata Insights — Check server information, version, and database structure on the fly to ensure system integrity.
Structured Access — Interact with your data using the modern ORDA model, ensuring consistency, type safety, and security.

The 4D MCP Server exposes 6 tools through the Vinkius. Connect it to Pydantic AI in under two minutes — no API keys to rotate, no infrastructure to provision, no vendor lock-in. Your configuration, your data, your control.

How to Connect 4D to Pydantic AI via MCP

Follow these steps to integrate the 4D MCP Server with Pydantic AI.

Install Pydantic AI

Run pip install pydantic-ai

Replace the token

Replace [YOUR_TOKEN_HERE] with your Vinkius token

Run the agent

Save to agent.py and run: python agent.py

Explore tools

The agent discovers 6 tools from 4D with type-safe schemas

Why Use Pydantic AI with the 4D MCP Server

Pydantic AI provides unique advantages when paired with 4D through the Model Context Protocol.

Full type safety: every MCP tool response is validated against Pydantic models, catching data inconsistencies before they reach your application

Model-agnostic architecture. switch between OpenAI, Anthropic, or Gemini without changing your 4D integration code

Structured output guarantee: Pydantic AI ensures tool results conform to defined schemas, eliminating runtime type errors

Dependency injection system cleanly separates your 4D connection logic from agent behavior for testable, maintainable code

4D + Pydantic AI Use Cases

Practical scenarios where Pydantic AI combined with the 4D MCP Server delivers measurable value.

Type-safe data pipelines: query 4D with guaranteed response schemas, feeding validated data into downstream processing

API orchestration: chain multiple 4D tool calls with Pydantic validation at each step to ensure data integrity end-to-end

Production monitoring: build validated alert agents that query 4D and output structured, schema-compliant notifications

Testing and QA: use Pydantic AI's dependency injection to mock 4D responses and write comprehensive agent tests

4D MCP Tools for Pydantic AI (6)

These 6 tools become available when you connect 4D to Pydantic AI via MCP:

create_entity

Requires a JSON string representation of the data payload. Create a new record in the database

delete_entity

Delete a record from the database

get_catalog

Retrieve the database catalog definition

get_entity

Get a specific record by primary key

list_entities

Supports ORDA-style query parameters like $filter and $orderby for advanced lookups. Query records from a specific DataClass (table)

update_entity

Requires a JSON string payload. Update an existing record in the database

Example Prompts for 4D in Pydantic AI

Ready-to-use prompts you can give your Pydantic AI agent to start working with 4D immediately.

"Show me the first 5 records from the 'Invoices' table."

"What tables (DataClasses) are exposed in my 4D catalog?"

"Create a new record in the 'Customers' table for 'John Doe' with email 'john@example.com'."

Troubleshooting 4D MCP Server with Pydantic AI

Common issues when connecting 4D to Pydantic AI through the Vinkius, and how to resolve them.

MCPServerHTTP not found

Update: pip install --upgrade pydantic-ai

4D + Pydantic AI FAQ

Common questions about integrating 4D MCP Server with Pydantic AI.

How does Pydantic AI discover MCP tools?

Create an MCPServerHTTP instance with the server URL. Pydantic AI connects, discovers all tools, and generates typed Python interfaces automatically.

Does Pydantic AI validate MCP tool responses?

Yes. When you define result types as Pydantic models, every tool response is validated against the schema. Invalid data raises a clear error instead of silently corrupting your pipeline.

Can I switch LLM providers without changing MCP code?

Absolutely. Pydantic AI abstracts the model layer. your 4D MCP integration works identically with OpenAI, Anthropic, Google, or any supported provider.