How to Use the Juhe Data / 聚合数据 MCP in Google ADK

Q: How do I connect the Juhe Data / 聚合数据 MCP toolset to a Google ADK agent?

You'll use the McpToolset class from the Google ADK, pointing it to your Vinkius server URL. Then you just pass that toolset into the tools parameter when you create your LlmAgent. The agent handles the rest.

Q: Can I use this to verify user identity in my Google Cloud application?

Yes, the getidcardinfo tool is designed for that. You can build a Google ADK agent that acts as a verification service, callable from your main application. This keeps the logic clean and contained within the agent.

Connect Google ADK agents to China's API ecosystem. Go from BigQuery insights to real-world action with Juhe Data.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Juhe Data / 聚合数据 MCP to Google ADK

Create your Vinkius account to connect Juhe Data / 聚合数据 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 Juhe Data / 聚合数据 with Google ADK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Act on Enterprise Data at Scale

Your Gemini agent can analyze millions of rows in BigQuery, identify a market trend, and then immediately act on it. With this toolset, it can query `get_exchange_rate` for multiple currencies or pull `get_oil_price` data to validate its hypothesis against real-world conditions. This isn't just about fetching data points. It's about closing the loop between large-scale analysis and immediate action. Your agent, running on Google Cloud, can now interact with external Chinese market APIs as if they were another internal service.

Power Localized Operations in China

Build agents that manage on-the-ground logistics and operations inside China. An agent can use `get_weather` to check conditions in a specific city, `get_calendar_day` to see if a factory is closed for a public holiday, and `get_ip_lookup` to verify a user's region. These tools give your agent the local context that's usually missing. Instead of guessing, it can make informed decisions. This is perfect for automating supply chain notifications, regional marketing campaigns, or customer support for your Chinese user base.

Enrich Your Datasets with this MCP Server

Turn your static data into a live resource. An agent can take a list of IP addresses from a Google Sheet and enrich it with location data using `get_ip_lookup`. Or it could take a list of dates and append holiday information using `get_calendar_month`. The Google ADK makes it easy to pass data from services like BigQuery or Sheets to an agent. This MCP server provides the tools for that agent to add value to the data before writing it back. It's a straightforward way to build powerful data processing pipelines.

Setup guide

Set up Juhe Data / 聚合数据 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 Juhe Data / 聚合数据 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="Juhe Data / 聚合数据_agent",
    model="gemini-2.0-flash",
    instruction="You have access to Juhe Data / 聚合数据 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 Juhe Data / 聚合数据. 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 Juhe Data / 聚合数据 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 Juhe Data / 聚合数据 MCP in Google ADK

You'll use the `McpToolset` class from the Google ADK, pointing it to your Vinkius server URL. Then you just pass that toolset into the `tools` parameter when you create your `LlmAgent`. The agent handles the rest.

Absolutely. Gemini's large context window is a great fit for this. An agent can make several tool calls—like getting news with `get_latest_news` and then checking stock data—and reason over all the combined information to form a conclusion.

An enterprise agent could monitor a BigQuery table of shipment ETAs. If a shipment is going to a city where `get_weather` reports a severe storm, the agent could automatically flag the delivery for delay. That's the power of combining your internal data with this external MCP.

Yes, the `get_id_card_info` tool is designed for that. You can build a Google ADK agent that acts as a verification service, callable from your main application. This keeps the logic clean and contained within the agent.

Vinkius handles the security layer for the MCP server. When your Google ADK agent calls for Chinese ID card information, the request is routed through an authenticated, encrypted channel. The Vinkius server itself is stateless and doesn't log the PII, providing a secure conduit for the data.

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