How to Use the Fig Finance MCP in Google ADK

Q: How do I connect the Fig Finance MCP Server to my Google ADK agent?

You initialize the McpToolset with the Fig Finance server URL and pass it to your Google ADK LlmAgent. This exposes tools like listcustomers and getcustomer to your Gemini model immediately within your Google ADK workflow.

Q: Can I restrict which Fig Finance tools my Google ADK agent can access?

Yes, you can use the toolnames filter in the Google ADK configuration to only expose specific Fig Finance tools. For example, you can allow getloanstatus while blocking disbursefunds for read-only Google ADK agents.

Q: How does Gemini's long context benefit Fig Finance analysis in Google ADK?

With Google ADK, you can pass years of repayment data from getrepayments directly into Gemini's 1M+ token window. The Google ADK model analyzes the entire repayment history alongside Fig Finance customer profiles to predict future default risks.

Q: How does Google ADK protect Fig Finance transaction logs and wallet balances?

All Google ADK calls to listtransactions and getbalance run through ephemeral V8 sandboxes that store no data. Your Google ADK environment communicates directly with the secure Fig Finance API, keeping sensitive ledger balances isolated from persistent third-party storage.

Analyze Fig Finance portfolios in Google ADK using Gemini's 1M token context to trigger disbursements directly.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Fig Finance MCP to Google ADK

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity

BigQuery-Powered Fig Finance Underwriting

When you run Google ADK with Gemini, you can feed massive customer histories directly into your agent's context window using this MCP server. Your Google ADK agent queries `get_loan_offers` and matches those offers against your internal BigQuery risk tables to make highly informed Fig Finance lending decisions. Once the Google ADK model determines the risk profile, it calls `apply_for_loan` using the exact parameters verified by your BigQuery data warehouse. You get a direct, automated bridge between your Google Cloud infrastructure and active Fig Finance lending operations.

High-Volume Fund Disbursements

Large-scale lending operations need reliable execution, which is why this Google ADK integration exposes the Fig Finance `disburse_funds` tool directly to your cloud-hosted agent. Gemini can process thousands of lines of transaction logs from `list_transactions` to verify which accounts are cleared for Fig Finance payouts. The Google ADK agent then executes the payout and monitors the progress via `get_loan_status`. Because the Google ADK framework runs natively on Google Cloud, you can trigger these Fig Finance workflows from Pub/Sub events or Cloud Functions.

Portfolio Monitoring via Google ADK

Keep a close eye on your outstanding capital using this MCP integration. Your Google ADK agent can run scheduled checks using `list_loans` to build a complete map of your active Fig Finance liabilities. The Google ADK agent combines this with `get_repayments` to track incoming cash flow against your operational Fig Finance targets. If the agent notices a discrepancy, it pulls the current wallet balance using `get_balance` to check your Fig Finance liquidity.

Setup guide

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

You initialize the `McpToolset` with the Fig Finance server URL and pass it to your Google ADK `LlmAgent`. This exposes tools like `list_customers` and `get_customer` to your Gemini model immediately within your Google ADK workflow.

Yes, you can use the `tool_names` filter in the Google ADK configuration to only expose specific Fig Finance tools. For example, you can allow `get_loan_status` while blocking `disburse_funds` for read-only Google ADK agents.

With Google ADK, you can pass years of repayment data from `get_repayments` directly into Gemini's 1M+ token window. The Google ADK model analyzes the entire repayment history alongside Fig Finance customer profiles to predict future default risks.

Yes, Google ADK can connect to the Fig Finance MCP server using either transport method. For cloud-hosted Google ADK agents, the streamable HTTP transport is highly recommended for stability.

All Google ADK calls to `list_transactions` and `get_balance` run through ephemeral V8 sandboxes that store no data. Your Google ADK environment communicates directly with the secure Fig Finance API, keeping sensitive ledger balances isolated from persistent third-party storage.

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