How to Use the Brex MCP in OpenAI Agents SDK

Manage your corporate spend and issue virtual cards directly from your OpenAI Agents SDK agent.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Brex MCP to OpenAI Agents SDK

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Issue cards through OpenAI Agents SDK

Your agent uses `brex_create_card` to spin up unique virtual cards for specific SaaS subscriptions. This keeps your spending isolated and controlled without manual dashboard entries. Since you are using the OpenAI Agents SDK, the built-in guardrails validate these requests before they hit the Brex API. Your agent handles the card creation while you keep the oversight.

Track cash flow within OpenAI Agents SDK

Call `brex_get_balance` to pull your current cash position into your agent's reasoning loop. You'll see exactly what is available in your Brex accounts without leaving your code. This MCP Server provides the raw data your agents need to make real-time financial decisions. It turns your OpenAI Agents SDK environment into a command center for your treasury.

Automate vendor payments via OpenAI Agents SDK

Use `brex_pay_vendor` to trigger payments to saved vendors inside your AP flow. Your agent identifies the vendor and executes the transfer based on your specific logic. Integrating this tool with your OpenAI Agents SDK pipeline ensures that every transaction is logged and traced. It removes the friction of manual AP entry while maintaining strict control over outgoing funds.

Setup guide

Set up Brex 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 Brex tools at runtime.
3

Create your Agent

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

Run the agent

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

You configure the MCPServerStreamableHttp endpoint within your agent's constructor. This connects the Brex tools to your agent, allowing for immediate execution of financial tasks.

Yes, you can filter available tools during the initialization of your agent. This ensures your agent only touches the specific Brex functions you authorize.

Yes, you can use the built-in tracing features of your agent to capture every interaction with the Brex API. This keeps a clear audit trail of your financial activity.

The server operates in an ephemeral V8 sandbox, ensuring your financial data is not stored permanently. Your sensitive credit card and bank account details never persist outside of the active session.

The agent will catch the error immediately and report the failure back to your logs. You can then review the state of the transaction before taking further action.

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