How to Use the Brex MCP in LlamaIndex

Ground your LlamaIndex RAG in real financial data. Connect Brex to build a searchable knowledge base of your company spending.

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 LlamaIndex

Create your Vinkius account to connect Brex to LlamaIndex 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 LlamaIndex

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Index Brex transactions in LlamaIndex

Use `brex_list_transactions` to pull historical data into your vector store. LlamaIndex then indexes these records, allowing you to query your spending history using natural language. Stop digging through CSVs. You can ask your agent about specific vendor trends or monthly burn rates, and it retrieves the answer from your indexed Brex data.

Query budgets using LlamaIndex

The `brex_list_budgets` tool feeds your knowledge base with current team allocations. Your agent understands which teams have remaining capacity before you decide on new spending. This setup creates a live view of your financial state. You query the index to get grounded, accurate data that reflects your actual company account status.

Search vendor lists via LlamaIndex

Populate your search index with your active vendor directory using `brex_list_vendors`. Your agent quickly identifies existing entries to prevent duplicate accounts. This keeps your AP records clean. When you search for a vendor, your agent identifies the match based on the actual entries stored in your Brex account.

Setup guide

Set up Brex MCP in LlamaIndex

Prerequisites

Python 3.10+ installed
llama-index-tools-mcp package
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run pip install llama-index-tools-mcp llama-index-llms-openai. The MCP tools package provides BasicMCPClient and McpToolSpec.
2

Connect with BasicMCPClient
Point BasicMCPClient to your Vinkius endpoint URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. Supports SSE and Streamable HTTP transports.
3

Convert to LlamaIndex tools
Call mcp_tool_spec.to_tool_list_async() to convert all Brex MCP tools into native FunctionTool objects that any LlamaIndex agent can use.
4

Run with any LLM
Create a FunctionAgent with the tools and your preferred LLM. Swap OpenAI for Anthropic, Gemini, or any LlamaIndex-supported provider.

agent.py

from llama_index.tools.mcp import BasicMCPClient, McpToolSpec
from llama_index.core.agent.workflow import FunctionAgent
from llama_index.llms.openai import OpenAI

# Connect to the MCP
mcp_client = BasicMCPClient(
    "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
)
mcp_tool_spec = McpToolSpec(client=mcp_client)

# Convert MCP tools to LlamaIndex tools
tools = await mcp_tool_spec.to_tool_list_async()

# Create and run the agent
agent = FunctionAgent(
    tools=tools,
    llm=OpenAI(model="gpt-4o"),
    system_prompt="You have access to Brex tools.",
)
response = await agent.run("List recent Brex data")

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 LlamaIndex

The MCP Server fetches raw JSON data from your account, which the LlamaIndex tool spec then converts into indexable nodes. These nodes are stored in your vector database for semantic search.

Your transaction records are stored in the vector database you control. The data is encrypted at rest and only accessible to the agents you authorize.

You can connect different Brex accounts to separate instances of this MCP Server. LlamaIndex then aggregates these sources into a unified knowledge base for your queries.

You can trigger re-indexing cycles whenever your agent calls a tool. This ensures your knowledge base stays current with the latest account activity.

The server accesses your card logs, vendor lists, and account balance records. It does not touch your tax documents, payroll data, or bank login credentials.

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