How to Use the Fintoc MCP in Google ADK

Q: How do I register the Fintoc MCP Server within my Google ADK agent?

You import McpToolset from the SDK and initialize it with your server's HTTP endpoint. Pass this toolset directly into the tools list of your LlmAgent to let Gemini discover the banking tools.

Q: Can I limit which Fintoc MCP tools my Google ADK agent can access?

Yes, you can pass a specific list of tool names to the McpToolset constructor. This lets you restrict a sensitive agent to only use listmovements while blocking payment creation tools like createpaymentintent.

Q: How does Gemini's long context benefit Fintoc operations in Google ADK?

Gemini can ingest thousands of transactions from listmovements in a single prompt. This allows the agent to find seasonal spending patterns or reconcile entire fiscal quarters without chunking the data.

Q: How does Google ADK protect sensitive Fintoc transaction history and account balances?

All financial data retrieved via listaccounts is processed within your Google Cloud project boundary. The server runs in an isolated sandbox, meaning your transaction histories are never used for model training and remain strictly within your VPC.

Run deep financial analysis in Google ADK by connecting Fintoc tools to Gemini's million-token context window.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Fintoc MCP to Google ADK

Create your Vinkius account to connect Fintoc 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 Fintoc with Google ADK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Analyze years of banking history in Google ADK

The `list_movements` tool pulls massive batches of transaction data directly into Gemini's long-context window. With Gemini's million-token limit, you can dump thousands of historical bank rows into a single prompt. The agent runs complex financial audits across these movements without losing context over long conversations. After isolating suspicious transactions with `get_movement`, it writes the clean dataset straight to BigQuery.

Automate high-volume payment routing

The `create_payment_intent` and `get_payment_intent` tools allow your agent to manage bank transfers based on real-time business events. When an unpaid invoice flags inside your BigQuery warehouse, the agent initiates the transfer instantly. Passing this MCP Server to your `LlmAgent` via `McpToolset` gives Gemini direct execution capabilities. To keep things secure, configure the toolset to expose only payment operations while isolating your read-only routines.

Map financial institutions across enterprise links

The `list_institutions` and `list_links` tools let your Google ADK agent discover available banks and active connections across your entire customer base. Before triggering a transfer, the agent checks which institutions support instant clearing. If a connection fails, calling `get_link` lets the agent diagnose the underlying bank error. It then dispatches a Pub/Sub message so your team can fix the link before users notice.

Setup guide

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

You import `McpToolset` from the SDK and initialize it with your server's HTTP endpoint. Pass this toolset directly into the `tools` list of your `LlmAgent` to let Gemini discover the banking tools.

Yes, you can pass a specific list of tool names to the `McpToolset` constructor. This lets you restrict a sensitive agent to only use `list_movements` while blocking payment creation tools like `create_payment_intent`.

Gemini can ingest thousands of transactions from `list_movements` in a single prompt. This allows the agent to find seasonal spending patterns or reconcile entire fiscal quarters without chunking the data.

Yes, the ADK supports both connection types. For production deployments on Vertex AI, using the Streamable HTTP transport ensures stable, asynchronous communication with your hosted server.

All financial data retrieved via `list_accounts` is processed within your Google Cloud project boundary. The server runs in an isolated sandbox, meaning your transaction histories are never used for model training and remain strictly within your VPC.

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