How to Use the Imagine.io MCP in Google ADK

Q: How do I connect Google ADK to the Imagine.io rendering tools?

Install the google-adk package and initialize the McpToolset with your Vinkius HTTP endpoint. Pass this toolset to your LlmAgent to instantly expose the 3D rendering capabilities via MCP to Gemini.

Q: Can Google ADK restrict which Imagine.io tools are exposed to the agent?

Yes. You can use the optional toolnames filter in Google ADK to expose only specific tools like createrenderjob or getjobstatus, keeping your agent focused solely on rendering.

Deploy enterprise-grade visual pipelines using Google ADK and the Imagine.io MCP Server to trigger 3D product renders directly.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Imagine.io MCP to Google ADK

Create your Vinkius account to connect Imagine.io 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 Imagine.io with Google ADK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Run high-volume 3D rendering pipelines

Connect your Gemini-powered enterprise agents directly to your 3D asset pipeline. Your agent uses `create_render_job` to initiate photorealistic renders of your retail inventory. By linking this tool to your BigQuery product tables, the agent can automatically trigger new renders whenever product specifications change. Instead of waiting around, the agent uses `get_job_status` to monitor the queue. Once complete, it fetches the output using `list_renders` and updates your cloud storage buckets, keeping your digital storefront updated with zero manual overhead.

Gemini long-context with this MCP Server

This integration allows your Google ADK agent to process massive catalogs in a single context window. The agent can call `list_products` and `list_scenes` to analyze thousands of product variations at once. Because Gemini handles up to 1M tokens, it can map complex material combinations across your entire catalog without losing track of the design rules. The agent uses `get_scene` and `list_materials` to match the correct textures to the right product models. It ensures that wood grains, metal finishes, and fabrics are applied accurately before sending the final job to the renderer.

Monitor render budgets and asset metadata

Enterprise rendering can quickly drain resources if left unchecked. Your Google ADK agent uses `get_account` to monitor your active credit balance before queueing large batches. This keeps your automated pipelines predictable and prevents unexpected billing spikes. Fetching details with `get_product` returns precise metadata for specific catalog items. This lets the agent verify that the dimensions and material assignments match your master inventory database before any rendering compute is spent.

Setup guide

Set up Imagine.io 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 Imagine.io 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="Imagine.io_agent",
    model="gemini-2.0-flash",
    instruction="You have access to Imagine.io 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 Imagine.io. 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 Imagine.io 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 Imagine.io MCP in Google ADK

Install the `google-adk` package and initialize the `McpToolset` with your Vinkius HTTP endpoint. Pass this toolset to your `LlmAgent` to instantly expose the 3D rendering capabilities via MCP to Gemini.

Yes. You can use the optional `tool_names` filter in Google ADK to expose only specific tools like `create_render_job` or `get_job_status`, keeping your agent focused solely on rendering.

Since renders run asynchronously, your Google ADK agent initiates the job with `create_render_job` and uses Gemini's reasoning capabilities to schedule periodic checks via `get_job_status` while continuing other tasks.

No. The MCP integration handles all communication. Your agent interacts directly with `list_scenes` and `list_materials` using standard tool calls, bypassing the need for custom integration code.

Your product metadata, material listings, and active render queues are processed in an isolated sandbox. We do not store or inspect the payloads of `list_products` or `get_product`. All credentials and session tokens are stored securely and never exposed to the LLM.

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