How to Use the Chuangkit / 创客贴 MCP in Google ADK

Q: How do I set up the Chuangkit / 创客贴 MCP Server inside the Google ADK?

You initialize the McpToolset with your Vinkius HTTP server URL and pass it to your LlmAgent. The ADK auto-discovers the tools and exposes them to your Gemini model.

Q: Can Gemini use Chuangkit / 创客贴 templates to generate new cloud-hosted assets?

Gemini reads the template layout via gettemplate and extracts the download assets with getasseturl. The Google ADK then passes these assets to your cloud storage buckets for further processing.

Connect Gemini's million-token context to Chuangkit / 创客贴 via Google ADK to analyze massive design libraries.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Chuangkit / 创客贴 MCP to Google ADK

Create your Vinkius account to connect Chuangkit / 创客贴 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 Chuangkit / 创客贴 with Google ADK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Massive Design Context Ingestion via Google ADK

This MCP Server feeds entire template libraries into Gemini's long-context window using `list_templates` and `list_categories`. The Google ADK passes thousands of design structures directly to the model, allowing it to spot trends across your entire Chuangkit catalog. Instead of making dozens of small API calls, Gemini processes the whole category list in one go. You get instant, deep analysis of your creative assets without hitting rate limits.

Cloud-Scale Material Tracking with Google ADK

The `list_materials` and `get_design_detail` tools let your enterprise agents sync active creative assets directly with BigQuery. The Google ADK manages this flow, writing design details straight to your cloud data warehouse for business intelligence reporting. You can run SQL queries on your design usage patterns right inside Vertex AI. This lets your agent automatically recommend templates based on real-world performance metrics.

Direct Template Discovery and Asset Retrieval

Using this MCP Server, your agent uses `search_templates` and `get_asset_url` to find and extract high-quality assets for marketing campaigns. The ADK maps these tools directly to Gemini's function calling interface, so the model knows exactly when to search and when to grab a download link. The retrieved URLs feed straight into your automated Google Cloud storage pipelines. This cuts out the manual download-and-upload step when updating ad creatives.

Setup guide

Set up Chuangkit / 创客贴 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 Chuangkit / 创客贴 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="Chuangkit / 创客贴_agent",
    model="gemini-2.0-flash",
    instruction="You have access to Chuangkit / 创客贴 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 Chuangkit / 创客贴. 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 Chuangkit / 创客贴 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 Chuangkit / 创客贴 MCP in Google ADK

You initialize the `McpToolset` with your Vinkius HTTP server URL and pass it to your `LlmAgent`. The ADK auto-discovers the tools and exposes them to your Gemini model.

Gemini reads the template layout via `get_template` and extracts the download assets with `get_asset_url`. The Google ADK then passes these assets to your cloud storage buckets for further processing.

Yes, the ADK supports both transports. For production cloud deployments, we recommend using the HTTP transport to keep your serverless functions stateless and fast.

Gemini uses its massive context window to process the full payload returned by the category list tool. It filters and categorizes the results internally without needing multiple round-trips.

Your template JSON payloads and design structures are processed in transient memory. No design data is used to train Google's models, and the transport layer is fully encrypted using enterprise-grade TLS.

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