How to Use the Plaid Enterprise Banking MCP in OpenAI Agents SDK

Q: How do I set up the Plaid Enterprise Banking MCP with the OpenAI Agents SDK?

Install openai-agents and create an MCPServerStreamableHttp instance with your Vinkius URL. Pass this server object into your Agent's constructor. The tools are discovered automatically, so there's no manual mapping.

Connect your OpenAI Agent to Plaid for production-grade banking actions, with built-in safety guardrails and full tracing.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers — Included with Plan

Connect Plaid Enterprise Banking MCP to OpenAI Agents SDK

Create your Vinkius account to connect Plaid Enterprise Banking to OpenAI Agents SDK — we handle the hosting, security, and runtime updates so you don't have to. No server setup required.

GDPR Included with Plan

Setup Plaid Enterprise Banking with OpenAI Agents SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Link Accounts, Fetch Balances

Start by connecting user bank accounts. Your agent calls `create_link_token` and then `exchange_public_token` to get a persistent access token. The OpenAI Agents SDK handles the tool discovery automatically, so you just tell the agent what to do. No boilerplate code. Once connected, your agent can pull real-time data using `get_accounts` and `get_balances`. With the SDK's built-in guardrails, you can set rules to prevent an agent from pulling balances too frequently, keeping your API costs in check. It's all logged in the OpenAI dashboard.

Analyze Transactions & Identity

Give your agent the tools to understand a user's financial history. The `get_transactions` tool pulls transaction data, which you can then pass to another specialized agent for analysis—like categorizing spending or flagging unusual activity. Need to verify who someone is? The `get_identity` tool provides account holder information. The OpenAI Agents SDK lets you create specific agents for sensitive tasks like this, with handoffs to ensure the right agent is handling the right data. This MCP Server gives your agents the raw financial data they need to operate.

The OpenAI Agents SDK MCP Server

Search for financial institutions and check their status. Your agent can use `search_institutions` to find a specific bank and then `get_institution` or `get_item_info` to confirm details and connection health. It's useful for building a reliable onboarding flow. This isn't just about calling APIs. The SDK's architecture means your agents discover these Plaid tools automatically. You just point it to the Vinkius endpoint, and the agent system figures out how to call `get_categories` or any other tool when needed.

Setup guide

Set up Plaid Enterprise Banking 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 Plaid Enterprise Banking tools at runtime.
3

Create your Agent

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

Run the agent

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

Install `openai-agents` and create an `MCPServerStreamableHttp` instance with your Vinkius URL. Pass this server object into your Agent's constructor. The tools are discovered automatically, so there's no manual mapping.

Yes. The OpenAI Agents SDK allows for handoffs between specialized agents. You can create one agent that only has access to `get_transactions` and another that only handles `get_identity`, ensuring strict separation of concerns.

This MCP Server is managed and sandboxed by Vinkius, handling auth and scaling for you. For the OpenAI Agents SDK, it means instant tool discovery and the ability to apply guardrails and tracing to banking operations without writing custom wrapper code.

No. The agent only invokes tools relevant to the user's request. OpenAI's function-calling models are trained to select the correct tool, like picking `get_balances` when asked for an account balance, and the SDK manages the execution.

Vinkius processes requests through ephemeral, zero-trust sandboxes, and never stores your data. The server only handles transaction, balance, and identity information in-transit. With the OpenAI Agents SDK, you get an extra layer of tracing to monitor exactly what data each agent accesses.

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