How to Use the Finmo MCP in OpenAI Agents SDK

Q: How do I configure the Finmo MCP Server inside the OpenAI Agents SDK?

Install the package via pip, then initialize the MCPServerStreamableHttp class with your Vinkius endpoint. Pass this server object in the mcpservers list when instantiating your OpenAI Agents SDK Agent.

Q: Can my OpenAI Agents SDK system handle Finmo currency exchanges in real time?

Yes. Your OpenAI agent calls getfxrate to fetch current market pricing, compares it to your Finmo wallet balances via listwallets, and then routes the transaction.

Q: What is the fastest way to register new buyers using this integration?

The OpenAI agent executes createcustomer to register the profile, then calls listpayinmethods to find regional options. It completes the flow by triggering createpayin to generate the deposit instructions.

Build production-ready financial agents with OpenAI Agents SDK and the Finmo 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 Finmo MCP to OpenAI Agents SDK

Create your Vinkius account to connect Finmo 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 Finmo with OpenAI Agents SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Dynamic FX and multi-currency treasury

Your OpenAI Agents SDK setup needs `get_fx_rate` to fetch real-time Finmo currency rates and manage cross-border exposure. This MCP Server exposes the live market pricing so your OpenAI agent checks rates before committing to any treasury movement. OpenAI Agents SDK uses built-in guardrails to validate Finmo values before running the code. By caching the tool schema with `cacheToolsList=True`, the OpenAI agent evaluates the Finmo wallet balances instantly without making redundant round-trips to find the right endpoint.

Automated payouts via OpenAI Agents SDK

Moving money out requires checking who gets paid, so your OpenAI agent calls `list_beneficiaries` to retrieve validated Finmo bank details. The OpenAI Agents SDK then maps them against active virtual accounts using `list_virtual_accounts`. If a Finmo payout bounces, your OpenAI agent checks `list_refunds` to reconcile the ledger. Handing off tasks between specialized OpenAI agents ensures that your compliance agent handles the refund while your payout agent focuses on sending successful transfers. This MCP Server setup avoids custom manual logic.

Instant pay-in reconciliation

Your OpenAI agent tracks incoming customer funds by calling `list_payins` and matching them to specific users. It uses `list_customers` to verify the buyer's identity and runs `list_payin_methods` to ensure they used the correct local payment rails. When a new buyer signs up, the OpenAI Agents SDK executes `create_customer` and instantly provisions a dedicated collection route via `create_payin`. The OpenAI dashboard records the entire trace, meaning you can audit exactly why an agent chose a specific payment method for a customer.

Setup guide

Set up Finmo 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 Finmo tools at runtime.
3

Create your Agent

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

Run the agent

Call Runner.run(agent, prompt) to execute. The agent invokes the appropriate Finmo 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="Finmo Agent",
            instructions="You have access to Finmo 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 Finmo. 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 Finmo 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 Finmo MCP in OpenAI Agents SDK

Install the package via pip, then initialize the `MCPServerStreamableHttp` class with your Vinkius endpoint. Pass this server object in the `mcp_servers` list when instantiating your OpenAI Agents SDK Agent.

Yes. Your OpenAI agent calls `get_fx_rate` to fetch current market pricing, compares it to your Finmo wallet balances via `list_wallets`, and then routes the transaction.

You define runtime guardrails in your OpenAI Agents SDK configuration before exposing the `create_payout` tool. The MCP Server exposes the right tools to enforce this step.

The OpenAI agent executes `create_customer` to register the profile, then calls `list_payin_methods` to find regional options. It completes the flow by triggering `create_payin` to generate the deposit instructions.

Your customer details, wallet balances, and payout histories are isolated within Vinkius's zero-trust V8 sandbox. This architecture handles all API token authentication on our side, preventing your OpenAI Agents SDK runtime from exposing raw Finmo credentials to the LLM.

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