How to Use the Finance Toolkit MCP in Google ADK

Q: How do I restrict which Finance Toolkit tools my Google ADK agent can see?

Use the toolnames parameter when initializing your McpToolset in Python. You can specify only calculateroi if you want to keep your Google ADK agent from running amortization tables, ensuring tight control over your enterprise agent's capabilities.

Q: How does Google ADK handle long financial tables from calculateamortization?

The calculateamortization tool returns structured SAC or PRICE tables. Because Gemini has a massive context window, the Google ADK can pass these large tables directly into the model's memory, allowing your agent to perform deep, multi-page financial analysis on the raw schedule.

Q: How do I configure the Finance Toolkit endpoint in Google ADK?

Install google-adk, import McpToolset and StreamableHttpServerParameters, then point the URL to your Vinkius endpoint. Pass this toolset into your LlmAgent constructor to give your Gemini models instant access to the MCP Server tools.

Feed exact amortization and interest calculations straight into your Google ADK enterprise agents on Gemini.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Finance Toolkit MCP to Google ADK

Create your Vinkius account to connect Finance Toolkit 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 Finance Toolkit with Google ADK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Connect Gemini to the Finance Toolkit via Google ADK.

Enterprise financial analysis requires absolute precision. This MCP Server hooks directly into your Google ADK pipelines, giving Gemini models access to mathematical calculations that they usually struggle to perform reliably. Your agent can now run `calculate_amortization` to generate SAC or PRICE tables without risking hallucinated payment schedules. Setting it up takes just a few lines of Python. Define your streamable HTTP server parameters, wrap them in the ADK toolset class, and pass them to your LlmAgent. Your Gemini models can now process massive financial datasets and run calculations in a single step.

Run ROI math directly on your BigQuery data.

If you store your corporate transaction ledgers in Google Cloud, your agents can pull raw numbers from BigQuery and feed them directly into `calculate_roi`. The Google ADK manages the flow, letting your agent fetch the investment costs, run the calculation, and output the exact return percentage. This structure avoids the need to export data to external spreadsheets. Your agent acts as a direct bridge between your secure BigQuery tables and the financial calculation tools, keeping your analysis entirely within your cloud perimeter.

Analyze long-horizon compound interest using Gemini.

Gemini's million-token context window lets you feed decades of financial reports into your agent. When analyzing long-term corporate debt, your agent can call the MCP Server to run `calculate_compound_interest` or `calculate_simple_interest` to project future liabilities based on historical data. You can use the ADK tool names filter to limit which tools are exposed to specific agents. This keeps your agent focused, ensuring it only calls the interest tools when analyzing debt structures, which saves execution time and keeps outputs clean.

Setup guide

Set up Finance Toolkit 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 Finance Toolkit 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="Finance Toolkit_agent",
    model="gemini-2.0-flash",
    instruction="You have access to Finance Toolkit 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 finance-toolkit. 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 Finance Toolkit 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 Finance Toolkit MCP in Google ADK

Use the `tool_names` parameter when initializing your `McpToolset` in Python. You can specify only `calculate_roi` if you want to keep your Google ADK agent from running amortization tables, ensuring tight control over your enterprise agent's capabilities.

Yes, the Google ADK supports both Stdio and HTTP transports. While Vinkius hosts the managed MCP Server via secure HTTP, you can configure your local environment to bridge standard input/output streams for testing before deploying to Google Cloud.

The `calculate_amortization` tool returns structured SAC or PRICE tables. Because Gemini has a massive context window, the Google ADK can pass these large tables directly into the model's memory, allowing your agent to perform deep, multi-page financial analysis on the raw schedule.

Install `google-adk`, import `McpToolset` and `StreamableHttpServerParameters`, then point the URL to your Vinkius endpoint. Pass this toolset into your `LlmAgent` constructor to give your Gemini models instant access to the MCP Server tools.

All financial parameters, including loan balances, interest rates, and payment frequencies, are processed inside an isolated, ephemeral V8 sandbox. Vinkius does not log or persist any of the raw numbers sent by your Google ADK agent, maintaining complete zero-trust data isolation.

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