How to Use the Finance Toolkit MCP in OpenAI Agents SDK

Q: How does caching work when using Finance Toolkit with OpenAI Agents SDK?

Set cacheToolsList=True when configuring your streamable HTTP server parameters in Python. This tells the OpenAI Agents SDK to cache the schemas of tools like calculateroi and calculatesimpleinterest, which reduces startup latency and saves API overhead on every agent run.

Spin up safe, multi-agent financial workflows using the OpenAI Agents SDK to run exact interest and amortization math.

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 OpenAI Agents SDK

Create your Vinkius account to connect Finance Toolkit to OpenAI Agents SDK 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 OpenAI Agents SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Auto-discover Finance Toolkit math inside OpenAI Agents SDK.

Stop hardcoding financial formulas into your system prompt. This MCP Server exposes four distinct tools directly to your OpenAI Agents SDK configuration. Once you register the server, your agent immediately knows how to fire off `calculate_amortization` to build SAC or PRICE tables, bypassing the risk of LLM math hallucinations. You do not have to write custom execution code. Just pass the streamable HTTP endpoint into your agent constructor, turn on `cacheToolsList=True` for speed, and let the SDK handle the rest.

Run safe compound calculations with built-in guardrails.

Running financial calculations in production requires strict boundaries. By hooking this MCP Server into your OpenAI Agents SDK setup, you can enforce validation rules before your agent triggers `calculate_compound_interest` or `calculate_simple_interest`. The agent gets the exact numbers it needs, and you get the peace of mind that it won't execute weird, out-of-bound variables. If a user asks for a projection, one specialized agent can run the math, verify the outputs against your guardrails, and hand off the clean dataset to a writer agent. Every step of this multi-agent exchange shows up clearly in your OpenAI dashboard tracing.

Track complex ROI calculations on your OpenAI dashboard.

When your agent runs `calculate_roi`, you need to know exactly what numbers went in and what came out. The integration with this MCP Server ensures that every single API call, payload, and tool response is fully logged. You can debug failing financial runs directly from your OpenAI dashboard without digging through raw terminal logs. This visibility keeps your production runs clean. When your agent calculates returns on investment, you see the exact input parameters and the resulting percentage output. It makes auditing your agentic financial decisions straightforward.

Setup guide

Set up Finance Toolkit MCP in OpenAI Agents SDK

Prerequisites

Python 3.10+ installed
openai-agents package (pip install openai-agents)
Active Vinkius subscription with a valid endpoint token

1

Install the SDK

Run pip install openai-agents to install the OpenAI Agents SDK. The MCP integration is built-in — no extra dependencies needed.
2

Connect via SSE transport

Use MCPServerSse with your Vinkius endpoint URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. The SDK auto-discovers all Finance Toolkit tools at runtime.
3

Create your Agent

Pass the MCP to Agent(mcp_servers=[server]). The agent receives Finance Toolkit tools as native definitions — JSON schemas resolve automatically.
4

Run the agent

Call Runner.run(agent, prompt) to execute. The agent invokes the appropriate Finance Toolkit tools and returns structured results. Copy the full example on the right to get started.

agent.py

import asyncio
from agents import Agent, Runner
from agents.mcp import MCPServerSse

async def main():
    async with MCPServerSse(
        url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    ) as server:
        agent = Agent(
            name="Finance Toolkit Agent",
            instructions="You have access to Finance Toolkit tools.",
            mcp_servers=[server],
        )
        result = await Runner.run(agent, "List recent transactions")
        print(result.final_output)

asyncio.run(main())

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 OpenAI Agents SDK

Install the SDK with pip, then initialize the streamable HTTP server using your Vinkius MCP Server endpoint. Pass this server object into your Agent constructor. The OpenAI Agents SDK automatically detects all four financial tools, making them instantly available for your agents to call.

Yes. You can set up a triage agent that recognizes financial queries and hands the conversation off to a dedicated math agent equipped with the Finance Toolkit. This math agent handles the `calculate_amortization` or `calculate_compound_interest` calls, then hands the clean results back to your primary agent.

Set `cacheToolsList=True` when configuring your streamable HTTP server parameters in Python. This tells the OpenAI Agents SDK to cache the schemas of tools like `calculate_roi` and `calculate_simple_interest`, which reduces startup latency and saves API overhead on every agent run.

The server expects decimal rates, like 0.05 for 5 percent. If your OpenAI Agents SDK agent passes an invalid format to `calculate_simple_interest`, the tool returns a clear error message. Your agent can then read this error, correct its input, and re-run the calculation automatically.

Your data is safe. Vinkius runs the Finance Toolkit in a zero-trust, ephemeral V8 isolate sandbox, meaning your interest rates, loan principals, and ROI inputs are never saved or stored. Your sensitive financial parameters are processed in memory and wiped the millisecond the calculation completes.

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