Connect your AI Agents to Brex in minutes

What is a Brex MCP?

It's an MCP server that lets your agents access data and functionality from Brex via tools. Your agents can invoke these tools to pull a card's recent transactions, check an expense's approval status, flag a receipt as missing, review a budget's remaining balance, and more.

Brex has its own MCP server. It covers expenses, transactions, budgets, and user lookups, but it doesn't include DLP controls, cross-connector Tool Packs, or centralized credential management, which is why teams often route through a platform like Merge Agent Handler instead.

How can I use the Brex MCP server?

The use cases naturally depend on the agent you've built, but here are a few common ones:

• Missing-receipt reminders: when an expense over a set amount has no attached receipt after a few days, an agent can message the employee with a link to upload it before the expense window closes

• Budget overspend alerts: when a team's budget crosses 90% of its allocated amount, an agent can post an alert to the budget owner with the remaining balance and days left in the period

• Expense policy violation flagging: an agent can scan new expenses for policy violations, like a meal over the per-diem cap or a purchase from a blocked merchant category, and route them to a manager for review

• Reconciliation against an accounting system: an agent can match Brex transactions against entries in NetSuite or QuickBooks and flag any that don't have a corresponding journal entry

What are popular tools for Brex's MCP server?

Here are some of the most commonly used tools:

• get_card_transactions returns recent transactions for a specific card. agents use it to spot duplicate charges or check spend against a limit

• list_expenses returns expenses filtered by status, employee, or date range. it's the fastest way for an agent to find every pending or unapproved expense in one call

• get_expense fetches full detail on a single expense, including receipt attachment status and approval state. agents call this after finding a candidate expense with a list operation

• list_budgets returns each budget's allocated amount, spent amount, and remaining balance. useful for any agent built around spend tracking or overspend alerts

• get_user looks up an employee's Brex profile by ID or email, including department and role. handy for routing approvals to the right manager

• list_bills returns vendor bills and their payment status. agents cross-reference this against accounting records during reconciliation

What makes Merge Agent Handler's Brex MCP server better than alternative Brex MCP servers?

Several things separate Merge Agent Handler's Brex MCP server from a self-hosted or community alternative:

• Enterprise-grade security and DLP: Merge Agent Handler includes built-in data loss prevention controls that let you block or redact sensitive fields before they reach an agent. For Brex, this means you can prevent card numbers, individual transaction amounts, or employee spend history from being exposed even when the agent has broad read access

• Managed authentication and credentials: Merge stores and refreshes Brex credentials on your behalf. You never expose raw API keys or OAuth tokens to an agent or manage token rotation manually

• Real-time observability and audit trail: Every tool call made against Brex is logged with timestamp, tool name, input parameters, and response metadata. You can audit exactly what an agent read or wrote without instrumenting anything yourself

• Tool Packs and controlled access: Tool Packs let you bundle specific Brex tools with tools from other connectors into a single MCP endpoint, scoped to a specific use case. An agent gets exactly the tools it needs, nothing more

How can I start using Merge Agent Handler's Brex MCP server?

You can take the following steps:

1. Create or log into your Merge Agent Handler account.

2. Install the Merge CLI by running pipx install merge-api, then run merge configure to link the CLI to your Merge account and merge login to authenticate your session.

3. Register the Agent Handler MCP server with Claude Code by running claude mcp add --transport http agent-handler https://ah-api.merge.dev/mcp, then open Claude Code and run /mcp to confirm agent-handler appears with a connected status.

4. Select agent-handler from the MCP list. This opens a browser window where you select which integrations to authenticate. Choose Brex and complete the auth flow. Merge stores and manages the credentials going forward.

5. Open a Claude Code session and start querying Brex data directly. The first time you use a Brex tool, a Magic Link may appear to complete connector authentication.

If you want to connect Merge Agent Handler's Brex MCP with internal or customer-facing agentic products, you can follow the steps in our docs.

Can employees use Merge to connect their AI tools to Brex?

Yes, Merge for Workforce lets your employees connect Claude, ChatGPT, Microsoft Copilot, Cursor, Codex, and other MCP-compatible AI tools to Brex without bypassing IT governance.

Instead of setting up direct connections with personal credentials that IT can't monitor or revoke, each employee authenticates through Merge and gets individual credentials tied to their identity. An employee can ask their AI to check a card's recent transactions, submit a missing receipt, or check an expense's approval status, all within IT-defined permissions.

IT also provisions access by role or group via SCIM. A finance analyst, for example, might get Brex access to reconcile transactions, NetSuite access to post journal entries, and Slack access to post budget alerts, while an engineering manager might get Brex access to review team card spend, GitHub access to check deploy activity, and Jira access to update sprint tickets.

Every tool call an employee's AI makes to Brex is also inspected against your DLP rules and logged to a searchable audit trail, giving security teams full visibility into what data was accessed and by whom.