How to Use the Finance Toolkit MCP in LangChain

Run real-time amortization and yield math directly inside your LangChain decision chains using this MCP Server.

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 LangChain

Create your Vinkius account to connect Finance Toolkit 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 Finance Toolkit with LangChain

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Amortization modeling on this MCP Server

`calculate_amortization` lets your LangChain agent generate complete SAC or PRICE schedules on the fly. You feed the output of a database fetch directly into this tool, turning raw loan terms into structured payment tables. Because LangChain handles sequential execution, the resulting schedule immediately feeds the next node in your chain. Developers trace the exact math and token usage in LangSmith to keep execution costs in check.

Automated ROI validation in LangGraph

`calculate_roi` evaluates the return percentage of an investment based on cost and gain inputs. Your agent triggers this calculation inside a custom loop to filter out low-performing assets before passing data to your database. Instead of writing custom Python math nodes, you use this standardized tool. It keeps your LangChain code clean and offloads the arithmetic to a secure, isolated runtime.

Compound interest chains

`calculate_compound_interest` computes exponential growth over defined compounding frequencies. The tool accepts periodic rates and returns exact future values, letting your agent project long-term portfolio values. LangChain chains pass these outputs to vector stores or email generators without manual parsing. It prevents math errors when your agent handles complex financial forecasting.

Setup guide

Set up Finance Toolkit 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 Finance Toolkit 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({
    "finance-toolkit-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 Finance Toolkit 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 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 LangChain

You install the adapter package and pass the MCP Server URL to the client. The adapter automatically registers the four calculation tools so your agent can call them during a run.

Yes, every call to the tools shows up in your LangSmith dashboard. You see the raw inputs, the execution latency, and the exact JSON output.

Your LangChain agent reads the user's prompt, determines the required amortization type, and maps it to the tool. The tool returns the correct table format based on the parameter.

Yes, you can aggregate this server alongside database or web-search servers using the LangChain multi-server client. This lets your agent fetch live interest rates from the web and immediately run them through `calculate_simple_interest`.

The tool runs in an isolated sandbox and never stores your loan amounts, interest rates, or ROI metrics. All calculations happen in memory and vanish the moment the session ends.

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