How to Use the QingFlow MCP in Google ADK

Q: Can the agent fetch the schema of an app dynamically?

Yes. The agent calls getappschema to understand the field types of any application before it attempts to write data using createrecord.

Connect Gemini-powered Google ADK agents to the QingFlow MCP Server to trigger workflows and manage database records.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers — Included with Plan

Connect QingFlow MCP to Google ADK

Create your Vinkius account to connect QingFlow to Google ADK — we handle the hosting, security, and runtime updates so you don't have to. No server setup required.

GDPR Included with Plan

Setup QingFlow with Google ADK

Ask AI about this MCP

ChatGPT

Claude

Perplexity Vinkius runs on Gemini

Gemini

Grok

Feed BigQuery data directly into QingFlow records

Build an agent using Google ADK that pulls warehouse data from BigQuery and updates your business applications in real-time. The agent can look up customer statuses in Google Cloud and use `create_record` to sync that information back to your active database. Because the ADK handles tool execution natively, your agent can compare values returned by `list_data` against your cloud data lake. This bridges the gap between your analytical databases and operational workflows.

Analyze long-context workflows with Gemini and MCP

Put Gemini's million-token context window to work by feeding entire workflow histories retrieved via `list_workflows` directly to your agent. The Google ADK lets the model analyze massive arrays of records returned by `list_data` without running out of memory. This setup allows the agent to spot bottlenecks across thousands of historical runs. It can then pinpoint exactly which user from `list_users` is stalling the queue and draft a targeted follow-up.

Secure your enterprise Google ADK integrations

Deploy your agent inside your Google Cloud environment and connect to the server via standard MCP transport protocols. The ADK supports both Stdio and HTTP transports, letting you lock down your network configuration. You can also use the tool names filter to restrict access. If you do not want an agent deleting data, simply exclude `delete_record` from the exposed toolset during initialization.

Setup guide

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

Yes, you can pass a tool names filter to the toolset configuration in Python. This lets you block high-risk actions like `delete_record` while keeping read-only tools active.

The ADK works with Gemini's massive context window, meaning you can pull large arrays of records via `list_data` without crashing the context. The model digests the entire list in one turn.

Use the McpToolset class from the Python package and point it to the Vinkius HTTP endpoint. Pass this toolset directly into your LlmAgent constructor.

Yes. The agent calls `get_app_schema` to understand the field types of any application before it attempts to write data using `create_record`.

This MCP server runs entirely inside an isolated, ephemeral V8 container. All schema details and workflow statuses pass through ephemeral memory; Vinkius handles the API token encryption, meaning your private database keys are never exposed to the LLM or stored on external servers.

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