How to Use the Fig Finance MCP in LangChain

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

Install langchain-mcp-adapters and initialize the MultiServerMCPClient with your Vinkius endpoint to expose Fig Finance tools. Pass the tools retrieved from client.gettools() directly into your LangChain agent constructor to start executing loan operations.

Run multi-step lending workflows in LangChain by connecting your agent directly to Fig Finance ledger tools.

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 LangChain

Create your Vinkius account to connect Fig Finance to LangChain 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 LangChain

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Onboard and score Fig Finance borrowers inside LangChain

The `create_customer` tool registers a new borrower and immediately feeds their profile into your active LangChain run. Your LangChain agent reads the profile data, evaluates creditworthiness using your custom chain logic, and instantly triggers `get_loan_offers` to fetch personalized lending terms from Fig Finance. By chaining these Fig Finance tool outputs together in LangChain, you don't have to write glue code to pass customer IDs between API endpoints. The output of the registration step flows directly into the evaluation step, allowing your LangChain agent to make immediate lending decisions.

Automate payouts with the Fig Finance MCP Server

The `apply_for_loan` tool submits the borrower's selection to Fig Finance, initiating the formal lending contract within your LangChain agent. Once approved, the LangChain agent calls `disburse_funds` to release the money to the customer's wallet without manual approval steps. LangSmith tracks every transition in this Fig Finance pipeline, giving you a clear view of tool latency and input parameters. If a disbursement fails or stalls, the LangChain agent catches the error in the chain and immediately polls `get_loan_status` to diagnose the issue.

Audit Fig Finance repayments using LangChain chains

The `get_repayments` tool pulls the complete payment schedule for any active Fig Finance loan directly into your LangChain context. Your LangChain agent uses this schedule to cross-reference outstanding debt against the current wallet holdings returned by `get_balance`. This MCP integration lets you build automated LangChain collections agents that notify customers when a payment is due. By combining these Fig Finance financial tools with LangChain vector stores, your agent can even draft personalized payment reminders based on historical customer interactions.

Setup guide

Set up Fig Finance MCP in LangChain

Prerequisites

Python 3.10+ installed
langchain-mcp-adapters + langgraph packages
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run pip install langchain-mcp-adapters langgraph langchain-openai. The MCP adapters package converts MCP tools into native LangChain BaseTool objects.
2

Connect via HTTP transport
Use MultiServerMCPClient with "transport": "http" pointing to your Vinkius endpoint. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Create a ReAct agent
Pass the discovered tools to create_react_agent() from LangGraph. The agent automatically routes Fig Finance tool calls through the MCP protocol.
4

Run with any LLM
Swap ChatOpenAI for ChatAnthropic, ChatGoogleGenerativeAI, or any LangChain-compatible model. The MCP tools work identically across all providers.

agent.py

from langchain_mcp_adapters.client import MultiServerMCPClient
from langgraph.prebuilt import create_react_agent
from langchain_openai import ChatOpenAI

async with MultiServerMCPClient({
    "fig-finance-mcp": {
        "transport": "http",
        "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp",
    }
}) as client:
    tools = client.get_tools()

    agent = create_react_agent(
        ChatOpenAI(model="gpt-4o"),
        tools,
    )
    result = await agent.ainvoke({
        "messages": "List recent Fig Finance transactions"
    })
    print(result["messages"][-1].content)

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 LangChain

Install `langchain-mcp-adapters` and initialize the `MultiServerMCPClient` with your Vinkius endpoint to expose Fig Finance tools. Pass the tools retrieved from `client.get_tools()` directly into your LangChain agent constructor to start executing loan operations.

Yes, you can build LangChain chains where the agent first calls `create_customer`, passes that output to `get_loan_offers`, and then executes `apply_for_loan`. LangGraph works best here to manage the state and conditional logic between these sequential Fig Finance tool calls.

LangSmith logs every single execution of Fig Finance tools like `disburse_funds` or `list_transactions` in real time during a LangChain run. You can inspect the exact JSON payloads, track execution latency, and debug failed loan applications without adding custom logging code to your LangChain application.

Your LangChain agent will catch the execution exception and can be programmed to immediately query Fig Finance via `get_loan_status`. You can design a fallback path in your LangChain chain to notify your team or retry the disbursement depending on the error code returned.

Vinkius runs the Fig Finance server in an isolated V8 sandbox, ensuring your customer records and transaction histories are never exposed to other environments during a LangChain run. Your API credentials stay encrypted on the Vinkius platform, so your LangChain code only needs a single secure endpoint token to access the lending tools.

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