How to Use the Brex MCP in Pydantic AI

Use Pydantic AI to enforce type-safe financial operations with your Brex account.

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 Pydantic AI

Create your Vinkius account to connect Brex to Pydantic AI 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 Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Validate Brex actions with Pydantic AI

Every response from `brex_list_cards` is checked against your Pydantic models the moment it arrives. If the Brex API returns a malformed field, your agent stops immediately. This prevents your Pydantic AI agent from acting on bad data or hallucinated card numbers. It ensures that your financial record-keeping remains strictly accurate.

Manage vendors using Pydantic AI

Use `brex_create_vendor` to add new payees to your AP system with full schema validation. Your agent ensures that every name and identifier matches your required structure. Since you are using Pydantic AI, you get an explicit error if the server output doesn't fit your model. This makes your vendor management process bulletproof and predictable.

Query users through Pydantic AI

Call `brex_list_users` to get a typed list of your employees and their associated accounts. Your agent processes these objects with full type hinting and runtime checks. This creates a reliable bridge between your corporate directory and your Pydantic AI agent. You get clean, validated data ready for internal logic and reporting.

Setup guide

Set up Brex MCP in Pydantic AI

Prerequisites

Python 3.10+ installed
pydantic-ai-slim[fastmcp] package
Active Vinkius subscription with a valid endpoint token

1

Install Pydantic AI with FastMCP
Run pip install "pydantic-ai-slim[fastmcp]". The FastMCP toolset replaces the deprecated MCPServerHTTP class with full protocol support.
2

Configure the FastMCPToolset
Pass a JSON-style config dict to FastMCPToolset with your Vinkius URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. Supports Streamable HTTP, SSE, and Stdio transports.
3

Create and run your agent
Pass the toolset to Agent(toolsets=[toolset]) and call agent.run(). Swap openai:gpt-4o for any supported model — Anthropic, Google, Mistral, or Groq.

agent.py

from pydantic_ai import Agent
from pydantic_ai.toolsets.fastmcp import FastMCPToolset

toolset = FastMCPToolset({
    "mcpServers": {
        "brex-mcp": {
            "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
        }
    }
})

agent = Agent(
    "openai:gpt-4o",
    toolsets=[toolset],
    system_prompt="You have access to Brex tools.",
)

result = await agent.run("List recent Brex transactions")
print(result.output)

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 Pydantic AI

Pydantic AI provides strict runtime validation of all tool responses. This prevents corrupt data from entering your agent's logic, which is critical for financial operations.

If a tool response violates your defined model, the agent raises a validation error. This forces an immediate stop, preventing any incorrect payments or data writes.

Yes, it supports both Streamable HTTP and SSE transports. You just need to point the MCPToolset to the running server instance.

Yes, all data containing personal identifiable information like employee names and email addresses is encrypted in transit. It is never logged in plaintext by the agent framework.

Yes, the framework is model-agnostic. You can run your agent locally while still benefiting from the strict type-safety provided by the MCP integration.

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