How to Use the 4D MCP in AutoGen

Q: How do I load 4D MCP tools into AutoGen?

Install autogen-extmcp. Initialize mcpservertools with your Vinkius URL and pass the resulting list directly into your AssistantAgent constructor.

Give your AutoGen multi-agent squads direct access to read, debate, and modify your 4D database records.

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 AutoGen

Create your Vinkius account to connect 4D to AutoGen 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 AutoGen

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Multi-Agent 4D Schema Analysis

The `get_catalog` tool feeds your database structure directly into an AutoGen conversation. A data-architect agent reviews the available DataClasses and debates with a developer agent about the best way to structure upcoming queries. This consensus-driven approach prevents bad calls to the MCP Server. The agents agree on the exact table relationships and required fields before executing any actual data retrieval.

Agents Negotiate ORDA Lookups

Fetching data becomes a collaborative effort when agents use `list_entities`. A performance-focused agent might push for strict `$filter` and `$orderby` parameters to limit payload size, while an analyst agent argues for broader results. Once they settle on the query, they execute it and review the MCP tool results together. If a specific record needs deeper inspection, one agent will call `get_entity` using the primary key they discovered during the initial search.

Consensus-Driven Database Mutations

AutoGen shines when modifying state via `create_entity` and `update_entity`. A writer agent drafts the JSON string payload, and a strict reviewer agent verifies the formatting against the catalog before allowing the tool execution. Removals require the same level of scrutiny. Before any agent triggers `delete_entity`, the squad verifies that dropping the record will not break related DataClasses or violate business rules.

Setup guide

Set up 4D MCP in AutoGen

Prerequisites

Python 3.10+ installed
autogen-ext[mcp] package
Active Vinkius subscription with a valid endpoint token

1

Install AutoGen with MCP
Run pip install "autogen-ext[mcp]" autogen-agentchat. The MCP extension includes mcp_server_tools for stateless tool access.
2

Fetch tools from the MCP
Call mcp_server_tools(SseServerParams(url=...)) with your Vinkius endpoint. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Run your agent
Pass the tools to AssistantAgent and call agent.run(). The agent invokes 4D tools and returns structured results.

agent.py

from autogen_ext.tools.mcp import SseServerParams, mcp_server_tools
from autogen_agentchat.agents import AssistantAgent
from autogen_ext.models.openai import OpenAIChatCompletionClient

server_params = SseServerParams(
    url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
)

tools = await mcp_server_tools(server_params)

agent = AssistantAgent(
    name="4D_assistant",
    model_client=OpenAIChatCompletionClient(model="gpt-4o"),
    tools=tools,
)

result = await agent.run("List recent 4D data")
print(result.messages[-1].content)

Get your connection token →

Prerequisites

Python 3.10+ installed
autogen-ext[mcp] + autogen-agentchat
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Same packages as above. McpWorkbench is ideal when your agent needs stateful sessions across multiple tool calls.
2

Use McpWorkbench as context manager
Wrap your agent in async with McpWorkbench(...) to maintain shared state and resources. The workbench manages the full MCP session lifecycle.
3

Run with workbench
Pass workbench=workbench to your agent. State is preserved across multiple tool calls within the same session.

agent.py

from autogen_ext.tools.mcp import McpWorkbench, SseServerParams
from autogen_agentchat.agents import AssistantAgent
from autogen_ext.models.openai import OpenAIChatCompletionClient

server_params = SseServerParams(
    url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
)

async with McpWorkbench(server_params) as workbench:
    agent = AssistantAgent(
        name="4D_assistant",
        model_client=OpenAIChatCompletionClient(model="gpt-4o"),
        workbench=workbench,
    )

    result = await agent.run("List recent 4D data")
    print(result.messages[-1].content)

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 AutoGen

Install `autogen-ext[mcp]`. Initialize `mcp_server_tools` with your Vinkius URL and pass the resulting list directly into your AssistantAgent constructor.

Any agent with the tool list in its configuration can invoke the operations. They usually coordinate in the chat to decide who should execute the call.

You design the system to require consensus. A reviewer agent must approve the primary key target before the execution agent is allowed to run the deletion tool.

The agents read the tool descriptions and schema first. If a query fails, they discuss the error message and rewrite the filter parameters until it works.

Vinkius handles auth via a single endpoint token while running the server in an ephemeral sandbox. Your proprietary database schemas and JSON entity payloads remain completely isolated from our storage.

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