4,500+ servers built on MCP Fusion
Vinkius
4D logo
Vinkius
OpenAI Agents SDK logo

How to Use the 4D MCP in OpenAI Agents SDK

Connect your 4D database directly to the OpenAI Agents SDK for production-ready, traced database operations.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

4D MCP on Cursor AI Code Editor MCP Client 4D MCP on Claude Desktop App MCP Integration 4D MCP on OpenAI Agents SDK MCP Compatible 4D MCP on Visual Studio Code MCP Extension Client 4D MCP on GitHub Copilot AI Agent MCP Integration 4D MCP on Google Gemini AI MCP Integration 4D MCP on Lovable AI Development MCP Client 4D MCP on Mistral AI Agents MCP Compatible 4D MCP on Amazon AWS Bedrock MCP Support
MCP Servers - Free for Subscribers
OpenAI Agents SDK

Connect 4D MCP to OpenAI Agents SDK

Create your Vinkius account to connect 4D to OpenAI Agents SDK 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

Auto-discover 4D schemas with this MCP Server

The `get_catalog` tool fetches the exact schema definition directly into your OpenAI agent's context. This happens automatically when you pass the server to your constructor, giving the LLM immediate awareness of available DataClasses. Guardrails built into the SDK ensure your agent actually verifies table structures before attempting inserts. When a specialized agent needs to add a record, it formats a JSON payload for `create_entity` and the framework validates the action against your safety constraints. Tracing in the OpenAI dashboard shows you exactly which tables the agent accessed.

Query ORDA endpoints with natural language

The `list_entities` tool handles the translation of ORDA-style query parameters like $filter and $orderby. Your OpenAI Agents SDK setup converts natural language into precise 4D lookups instantly. You get filtered database records back as structured context. Handoffs between specialized agents work perfectly here. A research agent can run `get_entity` to pull a specific primary key, then pass that exact record to a reporting agent. Building complex data extraction pipelines takes zero custom REST wrappers when using this MCP integration.

Execute database mutations safely

The `update_entity` tool requires a strictly formatted JSON payload to modify existing records. Your OpenAI agent constructs this payload based on user intent and pushes the changes back to your 4D backend. The SDK's built-in tracing logs the exact JSON sent to the API. Deletions demand strict oversight in production environments. Calling `delete_entity` triggers a direct removal of a record from the database. Because you define safety boundaries in the OpenAI framework, you control exactly which agents have permission to wipe data.

Setup guide

Set up 4D MCP in OpenAI Agents SDK

Prerequisites

  • Python 3.10+ installed
  • openai-agents package (pip install openai-agents)
  • Active Vinkius subscription with a valid endpoint token
  1. 1

    Install the SDK

    Run pip install openai-agents to install the OpenAI Agents SDK. The MCP integration is built-in — no extra dependencies needed.

  2. 2

    Connect via SSE transport

    Use MCPServerSse with your Vinkius endpoint URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. The SDK auto-discovers all 4D tools at runtime.

  3. 3

    Create your Agent

    Pass the MCP to Agent(mcp_servers=[server]). The agent receives 4D tools as native definitions — JSON schemas resolve automatically.

  4. 4

    Run the agent

    Call Runner.run(agent, prompt) to execute. The agent invokes the appropriate 4D tools and returns structured results. Copy the full example on the right to get started.

agent.py
import asyncio
from agents import Agent, Runner
from agents.mcp import MCPServerSse

async def main():
    async with MCPServerSse(
        url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    ) as server:
        agent = Agent(
            name="4D Agent",
            instructions="You have access to 4D tools.",
            mcp_servers=[server],
        )
        result = await Runner.run(agent, "List recent transactions")
        print(result.final_output)

asyncio.run(main())

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.

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 OpenAI Agents SDK

You initialize MCPServerStreamableHttp with your Vinkius endpoint. Pass that instance to the mcp_servers array in your Agent constructor. The SDK automatically discovers the database tools.
Yes, setting cacheToolsList=True prevents the agent from pulling the database schema on every turn. This drastically reduces latency when the agent runs multiple queries in a row.
The OpenAI dashboard logs every single tool call. You see the exact JSON payloads sent to the creation and update endpoints, along with the latency of the API response.
You assign the Vinkius endpoint only to specific specialized agents. A read-only agent gets an MCP connection filtered down to just the catalog and list tools, while a separate admin agent handles mutations.
Vinkius runs the connection inside a V8 Isolate Sandbox that destroys itself after the session ends. Your primary keys, ORDA queries, and JSON payloads never persist on our infrastructure. Auth requires just one ephemeral endpoint token.

Start using the 4D MCP today

We host it, we monitor it, we maintain it. You just paste one token.

Built & Managed by Vinkius 30s setup 6 tools

We've already built the connector for 4D. Just plug in your AI agents and start using Vinkius.

No hosting. No infrastructure. No complex setup.
All 6 tools are live and waiting. You're up and running in seconds.

Claude Claude
ChatGPT ChatGPT
Cursor Cursor
Gemini Gemini
Windsurf Windsurf
VS Code VS Code
JetBrains JetBrains
Vercel Vercel
+ other MCP clients

Vinkius gives your AI agents access to the full catalog of app connectors, all fully managed, secure, and enterprise-ready. One subscription, every tool you need.

Zero hosting required Full MCP catalog included Enterprise-grade security Auto-updated by Vinkius

Built, hosted, and secured by Vinkius. You just connect and go.