How to Use the Finch MCP in Google ADK

Q: How do I initialize the Finch MCP toolset within Google ADK?

You import McpToolset from the SDK and pass the server URL. This exposes tools like getindividual and getemployment directly to Gemini, allowing the model to decide when to call them during a conversation.

Q: Can Google ADK agents filter specific Finch tools?

Yes, you can pass a toolnames filter to the toolset parameter. This ensures your Gemini agent only sees tools like listdirectory and cannot access sensitive financial tools like listpaystatements.

Q: How do I check which HR platform a client is using?

Your agent can invoke listsupportedproviders to see the complete list of compatible platforms, or call getcompany to read the legal name and organizational details of the currently connected company.

Feed real-time HR and payroll data directly into your Google ADK pipelines via this MCP Server to automate workforce operations.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Finch MCP to Google ADK

Create your Vinkius account to connect Finch 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 Finch with Google ADK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Enrich BigQuery Warehouses with HR Data

Enterprise analytics require fresh personnel data. With this MCP Server, your Google ADK agent can call `list_directory` to fetch your active roster, then feed that structured data directly into BigQuery tables for SQL analysis. By combining Gemini's massive context window with tools like `get_employment`, your agent can ingest thousands of employee profiles at once. It can cross-reference department allocations and salary structures without hitting memory limits.

Run Deep Payroll Audits in Google ADK

Finding payroll anomalies across legacy systems is tedious. Your agent can query `list_pay_groups` and `list_pay_statements` to pull historical payment records, then use Vertex AI models to detect unusual variations or outliers. Since Google ADK connects directly to your cloud infrastructure, you can trigger these audits automatically on a schedule. The agent pulls the data, processes it, and writes the anomalies to a secure Cloud Storage bucket.

Automate Provider Status Checks

HR integrations break when underlying API credentials expire. This MCP server lets your agent run `introspect` and `get_me` to verify that the connection to the HRIS provider is active and has the required permissions before running bulk syncs. If a connection is degraded, the agent can alert your operations team with the exact failure reason. This keeps your data pipelines running smoothly without silent failures during nightly cron jobs.

Setup guide

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

You import `McpToolset` from the SDK and pass the server URL. This exposes tools like `get_individual` and `get_employment` directly to Gemini, allowing the model to decide when to call them during a conversation.

Yes, you can pass a `tool_names` filter to the toolset parameter. This ensures your Gemini agent only sees tools like `list_directory` and cannot access sensitive financial tools like `list_pay_statements`.

Gemini's million-token context allows the agent to ingest the entire payload from `list_directory` in a single pass. It can analyze complex organizational hierarchies without needing to chunk the data or make multiple redundant API calls.

Your agent can invoke `list_supported_providers` to see the complete list of compatible platforms, or call `get_company` to read the legal name and organizational details of the currently connected company.

Absolutely. All payroll records and tax details retrieved via `list_pay_statements` are processed in zero-trust, ephemeral MCP sandboxes. Vinkius never caches your HRIS payloads, and the connection tokens are encrypted end-to-end to ensure your financial data remains private.

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