How to Use the Chuanyun MCP in Google ADK

Q: Can Gemini write new records to Chuanyun using Google ADK?

Yes, the Google ADK agent uses createbizobject to write data directly. It will first call getformschema to make sure the payload matches your Chuanyun ERP requirements before attempting to write.

Q: How does Google ADK handle large Chuanyun databases?

The agent uses listbizobjects to paginate through Chuanyun records. Gemini's long context allows it to hold thousands of ERP records at once, making large-scale data analysis straightforward.

Feed Chuanyun ERP records directly into Google ADK to analyze workflows with Gemini's million-token context.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Chuanyun MCP to Google ADK

Create your Vinkius account to connect Chuanyun 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 Chuanyun with Google ADK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Analyze massive Chuanyun ERP datasets with Google ADK

Gemini's massive context window is perfect for digesting complex enterprise structures. By combining `list_biz_objects` and `get_form_schema`, your Google ADK agent pulls your entire Chuanyun schema and active records into a single reasoning step. This setup lets you run deep analysis on your operational bottlenecks without hitting context limits. The Google ADK agent can cross-reference active Chuanyun records against your BigQuery datasets to spot discrepancies instantly.

Automated workflow auditing on Google Cloud

You can track how long approvals take by letting your Google ADK agent query `get_workflow_history`. The agent extracts Chuanyun timestamps and transitions, mapping out bottlenecks in your business processes. Because the Google ADK runs natively on Google Cloud, you can automatically pipe these processed Chuanyun workflow histories directly into Vertex AI for predictive operational modeling.

Sync Google Cloud data using this MCP Server

Keeping your Chuanyun ERP updated with external cloud databases is simple. Your Google ADK agent reads incoming data streams and uses `create_biz_object` or `update_biz_object` to keep your records synchronized. If a Chuanyun record is no longer needed, the agent can call `delete_biz_object` to keep your database tidy. You control exactly which tools are exposed by filtering them in your Google ADK toolset configuration.

Setup guide

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

Install the ADK via pip, instantiate the HTTP MCP server parameters with your Vinkius URL, and register it inside your McpToolset. Pass that toolset directly to your LlmAgent to let Gemini interact with your Chuanyun ERP.

Yes, the Google ADK agent uses `create_biz_object` to write data directly. It will first call `get_form_schema` to make sure the payload matches your Chuanyun ERP requirements before attempting to write.

The agent uses `list_biz_objects` to paginate through Chuanyun records. Gemini's long context allows it to hold thousands of ERP records at once, making large-scale data analysis straightforward.

Yes, you can filter the tool list when initializing the McpToolset. Simply exclude `delete_biz_object` and `update_biz_object` to ensure the Google ADK agent cannot alter your Chuanyun ERP data. This gives you complete control over what tools the MCP server exposes.

Your Chuanyun ERP data, including business records and user lists retrieved by `list_users`, is sent directly to your Gemini model via secure transport. The Vinkius infrastructure runs in a zero-trust sandbox, meaning your ERP data is never cached or stored.

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