How to Use the AlisQI MCP in Google ADK

Q: Can Gemini analyze dynamic AlisQI fields using the Google ADK?

Yes, your agent calls listfields and listchoicelists to understand the exact structure of your active analysis sets. Gemini uses this structural map to format its queries when filtering through listresults.

Q: How does the agent know which analysis set to query?

The agent uses listanalysissets to find the correct ID matching your product line. From there, it pulls the specific metadata using getanalysissetdetails to execute highly targeted searches.

Run deep quality analysis on Gemini using the Google ADK to bridge your AlisQI records with BigQuery.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect AlisQI MCP to Google ADK

Create your Vinkius account to connect AlisQI 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 AlisQI with Google ADK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Cross-Reference AlisQI Results with BigQuery Data

`list_results` feeds raw quality metrics directly into your Gemini agent via the Google ADK. Because Gemini handles massive context windows, your agent can grab thousands of past test records and compare them against historical supply chain data stored in BigQuery. This deep context allows the agent to spot slow-moving drift in chemical mixtures or physical dimensions that standard database queries miss. You get proactive warnings before your production line drifts out of spec.

Restrict Exposed Tools in Your Google ADK Agent

`get_api_info` acts as the initial handshake to verify your connection status before running complex data pipelines. To prevent unauthorized modifications in your production environment, you can use the ADK's tool_names filter to expose only read-only tools like `get_result_details` to your public-facing agents. This selective exposure ensures your agent can read quality certificates without having the capability to modify active test protocols. It provides a clean way to build customer-facing tracking portals on Google Cloud.

Extract Insights from Documents with this MCP Server

`get_result_attachments` lets your Gemini agent ingest entire PDF certificates and lab reports directly from AlisQI through this MCP Server. The Google ADK passes these documents straight into Gemini’s long-context window, letting the model read handwriting, scanned stamps, and complex tables. Your agent then maps these unstructured findings back to your structured database using `store_results`. This automation eliminates the tedious manual entry step for your laboratory technicians.

Setup guide

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

You pass a list of allowed tool names to your McpToolset configuration when initializing the server parameters. This lets you restrict access to sensitive operations like `store_results` while leaving query tools open.

Yes, your agent calls `list_fields` and `list_choice_lists` to understand the exact structure of your active analysis sets. Gemini uses this structural map to format its queries when filtering through `list_results`.

Yes, you can connect using StreamableHttpServerParameters to point your agent to the Vinkius-hosted endpoint. This setup is ideal for serverless environments like Cloud Run where persistent connections are not practical.

The agent uses `list_analysis_sets` to find the correct ID matching your product line. From there, it pulls the specific metadata using `get_analysis_set_details` to execute highly targeted searches.

Your quality results, choice lists, and custom field definitions remain inside your private VPC. The Vinkius MCP Server runs in an isolated, single-tenant sandbox, ensuring that no training data leaks to public models.

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