How to Use the Brex MCP in AutoGen

Let your AutoGen agents debate financial decisions. Integrate Brex to enable consensus-based spend approval and management.

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 AutoGen

Create your Vinkius account to connect Brex to AutoGen 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 AutoGen

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Debate spend requests in AutoGen

Configure a security agent to check `brex_list_cards` while a finance agent evaluates the budget. They compare findings to decide if a new virtual card request is permitted. This prevents rogue spending. Agents challenge each other's conclusions based on the current financial data retrieved from the server.

Verify payments with AutoGen agents

Use `brex_get_balance` to inform your agents before they execute `brex_pay_vendor`. A performance agent pushes for speed, while a controller agent verifies cash availability. This multi-agent process ensures every payment is vetted. They only move forward once they reach a consensus that funds are sufficient.

Automate user onboarding in AutoGen

When a new hire is added, have your agents use `brex_create_user` to finalize their profile. One agent drafts the request, and another audits the details for accuracy. This minimizes errors during the setup process. You get a controlled, multi-step validation for every new team member you add to the company account.

Setup guide

Set up Brex MCP in AutoGen

Prerequisites

Python 3.10+ installed
autogen-ext[mcp] package
Active Vinkius subscription with a valid endpoint token

1

Install AutoGen with MCP
Run pip install "autogen-ext[mcp]" autogen-agentchat. The MCP extension includes mcp_server_tools for stateless tool access.
2

Fetch tools from the MCP
Call mcp_server_tools(SseServerParams(url=...)) with your Vinkius endpoint. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Run your agent
Pass the tools to AssistantAgent and call agent.run(). The agent invokes Brex tools and returns structured results.

agent.py

from autogen_ext.tools.mcp import SseServerParams, mcp_server_tools
from autogen_agentchat.agents import AssistantAgent
from autogen_ext.models.openai import OpenAIChatCompletionClient

server_params = SseServerParams(
    url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
)

tools = await mcp_server_tools(server_params)

agent = AssistantAgent(
    name="Brex_assistant",
    model_client=OpenAIChatCompletionClient(model="gpt-4o"),
    tools=tools,
)

result = await agent.run("List recent Brex data")
print(result.messages[-1].content)

Get your connection token →

Prerequisites

Python 3.10+ installed
autogen-ext[mcp] + autogen-agentchat
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Same packages as above. McpWorkbench is ideal when your agent needs stateful sessions across multiple tool calls.
2

Use McpWorkbench as context manager
Wrap your agent in async with McpWorkbench(...) to maintain shared state and resources. The workbench manages the full MCP session lifecycle.
3

Run with workbench
Pass workbench=workbench to your agent. State is preserved across multiple tool calls within the same session.

agent.py

from autogen_ext.tools.mcp import McpWorkbench, SseServerParams
from autogen_agentchat.agents import AssistantAgent
from autogen_ext.models.openai import OpenAIChatCompletionClient

server_params = SseServerParams(
    url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
)

async with McpWorkbench(server_params) as workbench:
    agent = AssistantAgent(
        name="Brex_assistant",
        model_client=OpenAIChatCompletionClient(model="gpt-4o"),
        workbench=workbench,
    )

    result = await agent.run("List recent Brex data")
    print(result.messages[-1].content)

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 AutoGen

You assign the Brex tools to an agent group. The agents use the tool outputs as evidence during their conversation, debating the findings until they agree on an action.

Yes, the conversation log captures every tool call and the resulting data. You can review the chat history to see exactly how your agents reached a financial decision.

The MCP Server enforces strict isolation for every request. Your agents only see the data you specifically grant them access to through the tool definitions.

You control the tool distribution in your AutoGen configuration. Only the agents you explicitly provide with the tool list can interact with your financial account.

Your financial information is processed in memory during the conversation and is not persisted outside your local environment. The Vinkius endpoint acts as a secure, ephemeral gateway for these operations.

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