How to Use the Fintoc MCP in OpenAI Agents SDK

Q: How do I initialize the Fintoc MCP Server in my OpenAI Agents SDK project?

Install the package using pip, then instantiate MCPServerStreamableHttp pointing to your hosted endpoint. Pass this server instance in the mcpservers list when constructing your agent to auto-discover the banking tools.

Q: Can an agent built with OpenAI Agents SDK execute Fintoc transactions autonomously?

Yes, the agent uses createpaymentintent to initiate transfers on its own. You should use the SDK's native guardrails to intercept these calls and require human approval before the transaction executes.

Get raw bank data and trigger payments directly within your OpenAI Agents SDK pipeline without manual API wrapping.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Fintoc MCP to OpenAI Agents SDK

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Run bank reconciliations with OpenAI Agents SDK

The `list_movements` and `get_movement` tools give your agents direct access to raw bank transaction histories. Instead of writing boilerplate cron jobs, your agent parses these transactions to match open invoices. Setting `cacheToolsList=True` in your `MCPServerStreamableHttp` configuration stops the agent from polling the Fintoc schema on every single turn. That keeps your reconciliation loops fast enough to prevent database locks on high-volume runs.

Secure payment execution with strict guardrails

The `create_payment_intent` tool lets your agent initiate bank-to-bank transfers directly from chat prompts. By locking down the schema parameters, you keep raw API keys hidden from the model entirely. Running this MCP Server inside the OpenAI Agents SDK lets you build a multi-agent verification system to intercept the intent. Your supervisor agent checks the amount against `get_payment_intent` before letting the transaction clear.

Manage bank links and account mapping

The `list_links` and `list_accounts` tools expose the connected financial institutions and their associated bank accounts to your system. Before trying to pull balances, your agent inspects these links to map out connected accounts. Whenever a link expires, the agent calls `get_link` to check the connection health. It then prompts the user for re-authentication, keeping your pipeline alive without hardcoding retry logic.

Setup guide

Set up Fintoc 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 Fintoc tools at runtime.
3

Create your Agent

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

Run the agent

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

Install the package using pip, then instantiate `MCPServerStreamableHttp` pointing to your hosted endpoint. Pass this server instance in the `mcp_servers` list when constructing your agent to auto-discover the banking tools.

Yes, the agent uses `create_payment_intent` to initiate transfers on its own. You should use the SDK's native guardrails to intercept these calls and require human approval before the transaction executes.

The SDK handles tool execution sequentially, but you should implement a backoff strategy when your agent calls `list_movements` repeatedly. This prevents hitting the underlying bank's API limits during heavy reconciliation runs.

No, the MCP Server handles all schema translation automatically. Your agent inspects the tool definitions at runtime, allowing it to call `get_account` or `list_institutions` without any custom translation layers.

Your bank credentials never pass through the LLM or the OpenAI platform. The SDK connects to the server via an ephemeral V8 sandbox, ensuring that sensitive transaction histories retrieved by `list_movements` remain encrypted in transit and are processed only within your local runtime memory.

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