How to Use the Finmei MCP in Google ADK

Q: How do I connect the Finmei MCP Server to Google ADK?

You initialize the McpToolset using your Vinkius HTTP URL and pass it to the Google ADK LlmAgent tool list. This makes all 12 Finmei financial tools available to Gemini models instantly.

Q: How does the Google ADK agent resolve mismatched Finmei tax codes?

The Google ADK agent first calls listtaxtypes to check valid tax rates in your Finmei account. It then matches the receipt data to the closest active Finmei tax rate before calling createexpense.

Run enterprise-grade Gemini agents that process your Finmei expenses and tax rates using the Google ADK framework.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Finmei MCP to Google ADK

Create your Vinkius account to connect Finmei 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 Finmei with Google ADK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Query Finmei records inside Google ADK pipelines

The `list_expenses` tool pulls raw Finmei transaction data directly into your Google ADK Gemini long-context window. Your Gemini agent analyzes thousands of historical rows at once, uncovering spending trends without pagination limits. You pass the MCP Server parameters to the ADK `McpToolset` constructor to expose these Finmei endpoints. The Google ADK agent then combines transaction outputs with BigQuery datasets for deep financial reporting.

Automate Finmei payment tracking with Google ADK

The `list_payments` tool retrieves Finmei payment histories to cross-reference against your Google ADK database records. Your enterprise Google agent runs this check hourly to flag unpaid invoices. If the Google ADK agent detects a missing record, it calls `get_payment` to pull specific Finmei metadata. This direct integration lets you reconcile Finmei books without manual spreadsheet exports.

Categorize Finmei corporate spending with Google ADK

The `list_categories` tool lists your active Finmei classifications to ensure clean bookkeeping inside Google ADK. Your Gemini agent maps incoming receipts to these precise Finmei categories before creating new entries. By using the MCP tools inside the ADK, you can limit the Gemini agent to only run `create_expense` and `list_tax_types`. This prevents the Google ADK model from invoking administrative tools like `delete_payment`.

Setup guide

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

You initialize the `McpToolset` using your Vinkius HTTP URL and pass it to the Google ADK `LlmAgent` tool list. This makes all 12 Finmei financial tools available to Gemini models instantly.

Yes, you can feed Finmei list outputs into Google ADK loops that invoke `update_expense` for multiple records. Gemini's massive context window handles these multi-turn Finmei updates without losing track of the schema.

Yes, the MCP handles both transport protocols out of the box within the ADK. For hosted enterprise Google ADK agents, we'd recommend the streamable HTTP transport to keep connections stateless.

The Google ADK agent first calls `list_tax_types` to check valid tax rates in your Finmei account. It then matches the receipt data to the closest active Finmei tax rate before calling `create_expense`.

All data transit between Google ADK and Finmei is encrypted using TLS 1.3. Your payment histories and tax rates are processed in ephemeral memory, meaning no Finmei records are cached or written to persistent disk.

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