Can the agent truly issue a real, functioning corporate card?

Yes! The `brex_create_card` logic specifically maps to creating a virtual limit card. By default, it operates completely valid via Visa/Mastercard configurations matching Brex internals. The agent handles setting its name and tying it strictly to the user id.

What acts as the final authentication key for Brex?

You only need a `User Token`. Brex explicitly supports personal workflow automation using `user_tokens` which perfectly mimic your permissions. It typically begins literally with the string `user_token_` followed by hashes.

Will vendor payments via AI require external 2FA from my side?

To enforce safety in the integration, the `approval_type` parameter when sending vendor money defaults to `'MANUAL'`. This means the AI structures all the math, formatting, routing inputs perfectly but leaves the final 'Accept' button queued on your dashboard.

How can I see my user lists across Brex?

Run a request on `brex_list_users`. The AI will natively stream the company's organizational tree mapping the emails to Brex UUIDs required for triggering corporate card injections.

Brex MCP Server for Pydantic AI 10 tools — connect in under 2 minutes

Name: Brex
Availability: InStock
Author: Vinkius

ai.pydantic.dev/mcp

Built by Vinkius GDPR 10 Tools SDK

Pydantic AI brings type-safe agent development to Python with first-class MCP support. Connect Brex through the Vinkius and every tool is automatically validated against Pydantic schemas — catch errors at build time, not in production.

Get MCP Server for AI Agents

ASK AI ABOUT THIS MCP SERVER

Open in ChatGPT Open in Claude Open in Perplexity

Vinkius supports streamable HTTP and SSE.

python

import asyncio
from pydantic_ai import Agent
from pydantic_ai.mcp import MCPServerHTTP

async def main():
    # Your Vinkius token — get it at cloud.vinkius.com
    server = MCPServerHTTP(url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp")

    agent = Agent(
        model="openai:gpt-4o",
        mcp_servers=[server],
        system_prompt=(
            "You are an assistant with access to Brex "
            "(10 tools)."
        ),
    )

    result = await agent.run(
        "What tools are available in Brex?"
    )
    print(result.data)

asyncio.run(main())

Fully ManagedVinkius Servers

60%Token savings

High SecurityEnterprise-grade

IAMAccess control

EU AI ActCompliant

DLPData protection

V8 IsolateSandboxed

Ed25519Audit chain

<40msKill switch

Stream every event to Splunk, Datadog, or your own webhook in real-time

* Every MCP server runs on Vinkius-managed infrastructure inside AWS - a purpose-built runtime with per-request V8 isolates, Ed25519 signed audit chains, and sub-40ms cold starts optimized for native MCP execution. See our infrastructure

About Brex MCP Server

The Brex MCP Server bridges standard large language models directly via the platform.brexapis.com to your startup's core spend engine. By delivering a single static User Token, you enable the most flexible financial assistant available.

Pydantic AI validates every Brex tool response against typed schemas, catching data inconsistencies at build time. Connect 10 tools through the Vinkius and switch between OpenAI, Anthropic, or Gemini without changing your integration code — full type safety, structured output guarantees, and dependency injection for testable agents.

What you can do

Agile Employee Onboarding — brex_create_user directly provisions employees with their associated hierarchical structure. Follow it up with brex_create_card to hand them digital spend capacity securely limited.
Accounting Snapshots — You don't need to load the Brex dash to trace down runaway expenses. Trigger brex_list_transactions to pull highly contextualized raw CSV data into your AI workspace.
Accounts Payable Controls — Draft and approve external entity vendors via brex_create_vendor and initiate routing payments brex_pay_vendor seamlessly, letting internal routing protocols map out the wires.

The Brex MCP Server exposes 10 tools through the Vinkius. Connect it to Pydantic AI in under two minutes — no API keys to rotate, no infrastructure to provision, no vendor lock-in. Your configuration, your data, your control.

How to Connect Brex to Pydantic AI via MCP

Follow these steps to integrate the Brex MCP Server with Pydantic AI.

Install Pydantic AI

Run pip install pydantic-ai

Replace the token

Replace [YOUR_TOKEN_HERE] with your Vinkius token

Run the agent

Save to agent.py and run: python agent.py

Explore tools

The agent discovers 10 tools from Brex with type-safe schemas

Why Use Pydantic AI with the Brex MCP Server

Pydantic AI provides unique advantages when paired with Brex through the Model Context Protocol.

Full type safety: every MCP tool response is validated against Pydantic models, catching data inconsistencies before they reach your application

Model-agnostic architecture — switch between OpenAI, Anthropic, or Gemini without changing your Brex integration code

Structured output guarantee: Pydantic AI ensures tool results conform to defined schemas, eliminating runtime type errors

Dependency injection system cleanly separates your Brex connection logic from agent behavior for testable, maintainable code

Brex + Pydantic AI Use Cases

Practical scenarios where Pydantic AI combined with the Brex MCP Server delivers measurable value.

Type-safe data pipelines: query Brex with guaranteed response schemas, feeding validated data into downstream processing

API orchestration: chain multiple Brex tool calls with Pydantic validation at each step to ensure data integrity end-to-end

Production monitoring: build validated alert agents that query Brex and output structured, schema-compliant notifications

Testing and QA: use Pydantic AI's dependency injection to mock Brex responses and write comprehensive agent tests

Brex MCP Tools for Pydantic AI (10)

These 10 tools become available when you connect Brex to Pydantic AI via MCP:

brex_create_card

Useful for giving employees isolated cards for SaaS subscriptions. Issue a dynamic Virtual Corporate Card

brex_create_user

You must provide a valid email, first name, and last name. Invite a new employee / user to Brex

brex_create_vendor

Create a Vendor in AP (Accounts Payable)

brex_get_balance

Get main cash balance of the Brex Cash accounts

brex_list_budgets

List budget programs assigned to teams

brex_list_cards

List all issued cards across the company

brex_list_transactions

Sweep historical Brex card and account transactions

brex_list_users

List all users in the Brex company account

brex_list_vendors

List saved Vendors inside Brex AP

brex_pay_vendor

Orchestrate a vendor payment (Send Money)

Example Prompts for Brex in Pydantic AI

Ready-to-use prompts you can give your Pydantic AI agent to start working with Brex immediately.

"Invite the new engineer 'John Carter' via email john@company.com into Brex. After you get his ID, spin him up a Virtual Card with a $1K limit immediately."

"Check the core cash settlement. How much Treasury base balance do we stand at? Extract only active Checking values."

"Pull all corporate expenses tracked over the past 30 days focusing entirely on our AWS hosting and digital footprints."

Troubleshooting Brex MCP Server with Pydantic AI

Common issues when connecting Brex to Pydantic AI through the Vinkius, and how to resolve them.

MCPServerHTTP not found

Update: pip install --upgrade pydantic-ai

Brex + Pydantic AI FAQ

Common questions about integrating Brex MCP Server with Pydantic AI.

How does Pydantic AI discover MCP tools?

Create an MCPServerHTTP instance with the server URL. Pydantic AI connects, discovers all tools, and generates typed Python interfaces automatically.

Does Pydantic AI validate MCP tool responses?

Yes. When you define result types as Pydantic models, every tool response is validated against the schema. Invalid data raises a clear error instead of silently corrupting your pipeline.

Can I switch LLM providers without changing MCP code?

Absolutely. Pydantic AI abstracts the model layer — your Brex MCP integration works identically with OpenAI, Anthropic, Google, or any supported provider.