How to Use the 4D MCP in Google ADK

Q: Can I limit which 4D tables Google ADK can access?

You use the toolnames parameter to restrict the agent. By exposing only the read tools, you prevent the LLM from accidentally modifying your database.

Give your Google ADK agents direct read and write access to your 4D database using Gemini's massive context window.

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 Google ADK

Create your Vinkius account to connect 4D to Google ADK 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 Google ADK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Map 4D schemas into your MCP Server context

The `get_catalog` tool pulls your entire 4D database definition directly into the Google ADK environment. Enterprise applications require exact knowledge of table structures before they run queries. Gemini's million-token context easily holds massive enterprise schemas without losing track of foreign keys or data types. Developers building on Google Cloud can cross-reference this catalog with BigQuery datasets. When your LlmAgent needs to join legacy records with cloud analytics, it knows exactly which DataClasses exist. Passing the McpToolset to your agent makes these schema details instantly available.

Query ORDA endpoints using Gemini

The `list_entities` tool pulls specific record sets using native ORDA syntax. Your Google ADK agent translates user questions into precise $filter and $orderby parameters. The resulting JSON dumps straight into Gemini's context window for reasoning. Finding an exact match is just as fast. Calling `get_entity` with a primary key retrieves a single database row. You can feed that specific record into Vertex AI pipelines or use it to enrich a BigQuery dashboard.

Manage 4D records from Google Cloud

The `create_entity` tool writes new data back to your legacy system using a valid JSON payload. The LlmAgent formulates this payload based on the catalog definition and pushes the new record to your database via the MCP connection. Transport happens over secure HTTP directly from your Google Cloud infrastructure. Modifying existing entries relies on the `update_entity` tool. If an agent needs to clean up old data, it can trigger `delete_entity` to wipe the record entirely. You restrict these destructive actions using the tool_names filter when initializing your toolset.

Setup guide

Set up 4D MCP in Google ADK

Prerequisites

Python 3.10+ installed
google-adk package (pip install google-adk)
Active Vinkius subscription with a valid endpoint token

1

Install Google ADK

Run pip install google-adk to install the Agent Development Kit. MCP support is included via the McpToolset class.
2

Connect via SSE transport

Use McpToolset.from_server() with SseServerParams pointing to your Vinkius endpoint. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Create an LlmAgent

Pass the returned mcp_tools list directly to LlmAgent(tools=mcp_tools). The ADK maps each MCP tool to a native Gemini function call — no manual schema definitions required.
4

Run with any Gemini model

The agent works with any Gemini model (gemini-2.0-flash, gemini-2.5-pro, etc.). Copy the full example on the right to get started with 4D tools in your ADK agent.

agent.py

from google.adk.agents import LlmAgent
from google.adk.tools.mcp_tool.mcp_toolset import McpToolset
from google.adk.tools.mcp_tool.mcp_session_manager import SseServerParams

# Connect to the MCP via SSE
mcp_tools, exit_stack = await McpToolset.from_server(
    connection_params=SseServerParams(
        url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    )
)

# Create your agent with auto-discovered tools
agent = LlmAgent(
    name="4D_agent",
    model="gemini-2.0-flash",
    instruction="You have access to 4D tools via MCP.",
    tools=mcp_tools,
)

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 Google ADK

Install the required package and wrap your Vinkius endpoint in StreamableHttpServerParameters. Pass that configuration into an McpToolset and hand it to your LlmAgent as an MCP toolset.

You use the tool_names parameter to restrict the agent. By exposing only the read tools, you prevent the LLM from accidentally modifying your database.

Gemini handles the translation from natural language to ORDA syntax perfectly. It passes the resulting $filter strings directly to the list endpoint.

Gemini models support contexts over one million tokens. Pulling the entire schema into memory rarely hits limits, letting the agent reason across hundreds of tables at once.

Every request routes through a zero-trust V8 Isolate Sandbox that processes your ORDA queries and immediately spins down. We never log your JSON payloads or primary keys. You authenticate with a single ephemeral 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