How to Use the isvat MCP in Google ADK

Q: How do I set up isvat in my Google ADK pipeline?

Initialize McpToolset with the HTTP transport parameters pointing to the Vinkius endpoint, then pass it to your LlmAgent. You can restrict tool access using the toolnames filter if your agent only needs to validate single IDs.

Q: Can Gemini models use isvat to process bulk tax lists in Google ADK?

Yes, the validatemultiplevat tool allows Gemini to check multiple European tax identifiers in one pass. The model parses the array response and correlates the tax status with your BigQuery customer tables.

Q: What happens if the VIES tax registry goes offline?

Your pipeline should call checkapistatus at the start of your run. If the registry is down, your Google ADK agent can gracefully pause the pipeline and alert your team via Google Cloud Logging.

Verify European tax IDs directly inside your Google ADK enterprise pipelines using this MCP Server.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect isvat MCP to Google ADK

Create your Vinkius account to connect isvat 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 isvat with Google ADK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Real-time tax validation from BigQuery datasets

`validate_eu_vat` checks European tax registration status directly from your Gemini models running on Google ADK. Your agent reads raw tax records from BigQuery, processes them, and flags anomalies instantly. This prevents bad tax data from corrupting your enterprise data warehouse. The agent runs the check natively, allowing your model to make decisions based on official VIES records.

Batch audit validation via MCP Server for high-volume billing

`validate_multiple_vat` allows your Google ADK agent to audit thousands of transactions concurrently. Gemini uses its long-context window to analyze the results of these batch validations alongside your transaction logs. Your agent uses this toolset to scan massive batches of customer records in a single run. You do not need to write custom batching logic in your Cloud Functions.

Proactive gateway health checks

`check_api_status` verifies the operational status of the VIES validation service before your Google ADK pipelines execute. This prevents your Gemini agents from running into timeout loops during scheduled Cloud Composer runs. This MCP connection handles the check before execution. The agent queries this tool first, then proceeds with tax audits only if the gateway is green. If it detects a failure, it routes the data to a manual review queue in Vertex AI.

Setup guide

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

Initialize `McpToolset` with the HTTP transport parameters pointing to the Vinkius endpoint, then pass it to your `LlmAgent`. You can restrict tool access using the `tool_names` filter if your agent only needs to validate single IDs.

Yes, the `validate_multiple_vat` tool allows Gemini to check multiple European tax identifiers in one pass. The model parses the array response and correlates the tax status with your BigQuery customer tables.

This MCP toolset registers tools that return structured JSON, which Gemini reads easily within its large context window. The model can process thousands of `validate_eu_vat` outputs without losing track of your business rules.

Your pipeline should call `check_api_status` at the start of your run. If the registry is down, your Google ADK agent can gracefully pause the pipeline and alert your team via Google Cloud Logging.

All EU VAT numbers sent through the server are processed in an ephemeral, zero-trust V8 sandbox. The tax identifiers are transmitted securely to government databases and are never cached or written to persistent storage.

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