How to Use the Argyle MCP in Google ADK

Q: How do I configure Argyle with Google ADK?

Install google-adk and initialize an McpToolset. Pass your Vinkius HTTP endpoint into StreamableHttpServerParameters, then add the toolset to your LlmAgent.

Q: Can I restrict which Argyle tools my Google ADK agent sees?

Yes. Use the toolnames filter when setting up the toolset. This limits the agent to specific operations like fetching income totals.

Connect Argyle to Google ADK and let Gemini agents analyze employment data directly alongside BigQuery.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Argyle MCP to Google ADK

Create your Vinkius account to connect Argyle 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 Argyle with Google ADK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Enterprise Income Analysis via MCP Server

Gemini's massive context window eats the raw output from the `get_income` and `list_payouts` tools alive. Your Google ADK agent pulls years of pay period details and cross-references them against your internal data stored in BigQuery. You just wrap the Vinkius URL in `StreamableHttpServerParameters` to establish the connection. Processing thousands of W-2s and 1099s used to require complex ETL pipelines. Now your LlmAgent fetches the exact financial breakdown it needs on demand. The framework feeds this structured data straight into Vertex AI for downstream machine learning tasks.

Automated Employment Verification

The `get_employment` tool dumps a candidate's complete work history into your Gemini agent's memory. Instead of writing custom API wrappers, you initialize an `McpToolset` and pass it to your agent constructor. It reads the schemas and executes the queries autonomously. Filtering exposed tools keeps your agents focused. If a specific agent only needs to verify identity, you use the `tool_names` parameter to restrict access to just the `list_identities` tool. This prevents the model from accidentally creating users when it shouldn't.

Managing HR Connections at Scale

Provisioning new accounts happens through the `create_user` and `list_users` tools. Your Google Cloud infrastructure handles the scale while the agent orchestrates the onboarding logic. Vinkius manages the MCP Server authentication layer so you only ever deal with a single endpoint token. Checking connection health is critical for enterprise deployments. The `get_account_check` tool lets your agent verify that a user's payroll account remains linked before attempting to pull new data. Everything executes over HTTP transport securely.

Setup guide

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

Install `google-adk` and initialize an `McpToolset`. Pass your Vinkius HTTP endpoint into `StreamableHttpServerParameters`, then add the toolset to your LlmAgent.

Yes. Use the `tool_names` filter when setting up the toolset. This limits the agent to specific operations like fetching income totals.

Yes. The framework supports both Stdio and HTTP transports natively. Vinkius provides the Streamable HTTP endpoint for your deployment.

The 1M+ token context window easily absorbs massive payroll arrays. Your agent can ingest hundreds of individual payouts without losing track of the user's employment timeline.

We prioritize zero-trust architecture. Vinkius routes the verified identity info and pay period details through an ephemeral sandbox. The data flows straight into your Google Cloud environment without persistent storage on our end.

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