playbooks

home / skills / composiohq / awesome-claude-skills / brex-automation

brex-automation skill

/brex-automation

This skill automates Brex tasks via Rube MCP by discovering current tool schemas before execution to ensure up-to-date, safe workflows.

npx playbooks add skill composiohq/awesome-claude-skills --skill brex-automation

Review the files below or copy the command above to add this skill to your agents.

Files (1)
SKILL.md
2.8 KB
---
name: brex-automation
description: "Automate Brex tasks via Rube MCP (Composio). Always search tools first for current schemas."
requires:
  mcp: [rube]
---

# Brex Automation via Rube MCP

Automate Brex operations through Composio's Brex toolkit via Rube MCP.

**Toolkit docs**: [composio.dev/toolkits/brex](https://composio.dev/toolkits/brex)

## Prerequisites

- Rube MCP must be connected (RUBE_SEARCH_TOOLS available)
- Active Brex connection via `RUBE_MANAGE_CONNECTIONS` with toolkit `brex`
- Always call `RUBE_SEARCH_TOOLS` first to get current tool schemas

## Setup

**Get Rube MCP**: Add `https://rube.app/mcp` as an MCP server in your client configuration. No API keys needed — just add the endpoint and it works.

1. Verify Rube MCP is available by confirming `RUBE_SEARCH_TOOLS` responds
2. Call `RUBE_MANAGE_CONNECTIONS` with toolkit `brex`
3. If connection is not ACTIVE, follow the returned auth link to complete setup
4. Confirm connection status shows ACTIVE before running any workflows

## Tool Discovery

Always discover available tools before executing workflows:

```
RUBE_SEARCH_TOOLS
queries: [{use_case: "Brex operations", known_fields: ""}]
session: {generate_id: true}
```

This returns available tool slugs, input schemas, recommended execution plans, and known pitfalls.

## Core Workflow Pattern

### Step 1: Discover Available Tools

```
RUBE_SEARCH_TOOLS
queries: [{use_case: "your specific Brex task"}]
session: {id: "existing_session_id"}
```

### Step 2: Check Connection

```
RUBE_MANAGE_CONNECTIONS
toolkits: ["brex"]
session_id: "your_session_id"
```

### Step 3: Execute Tools

```
RUBE_MULTI_EXECUTE_TOOL
tools: [{
  tool_slug: "TOOL_SLUG_FROM_SEARCH",
  arguments: {/* schema-compliant args from search results */}
}]
memory: {}
session_id: "your_session_id"
```

## Known Pitfalls

- **Always search first**: Tool schemas change. Never hardcode tool slugs or arguments without calling `RUBE_SEARCH_TOOLS`
- **Check connection**: Verify `RUBE_MANAGE_CONNECTIONS` shows ACTIVE status before executing tools
- **Schema compliance**: Use exact field names and types from the search results
- **Memory parameter**: Always include `memory` in `RUBE_MULTI_EXECUTE_TOOL` calls, even if empty (`{}`)
- **Session reuse**: Reuse session IDs within a workflow. Generate new ones for new workflows
- **Pagination**: Check responses for pagination tokens and continue fetching until complete

## Quick Reference

| Operation | Approach |
|-----------|----------|
| Find tools | `RUBE_SEARCH_TOOLS` with Brex-specific use case |
| Connect | `RUBE_MANAGE_CONNECTIONS` with toolkit `brex` |
| Execute | `RUBE_MULTI_EXECUTE_TOOL` with discovered tool slugs |
| Bulk ops | `RUBE_REMOTE_WORKBENCH` with `run_composio_tool()` |
| Full schema | `RUBE_GET_TOOL_SCHEMAS` for tools with `schemaRef` |

---
*Powered by [Composio](https://composio.dev)*

Overview

This skill automates Brex operations through Composio's Brex toolkit using the Rube MCP gateway. It guides tool discovery, connection checks, and schema-compliant execution so you can run payments, fetch account data, and perform bulk tasks reliably. Always search available tools first to avoid schema drift.

How this skill works

The skill uses RUBE_SEARCH_TOOLS to discover current tool slugs and input schemas, then verifies an active Brex connection via RUBE_MANAGE_CONNECTIONS. After discovery and connection validation, it executes operations with RUBE_MULTI_EXECUTE_TOOL or RUBE_REMOTE_WORKBENCH, passing schema-compliant arguments and a memory object. It handles session reuse and pagination tokens to ensure robust workflows.

When to use it

  • Automate Brex payments, reconciliations, or reporting tasks.
  • Integrate Brex workflows into agent-driven pipelines or CRON jobs.
  • Run bulk operations (batch payments, exports) safely via Composio toolchain.
  • When you need reliable schema discovery before each execution to avoid runtime errors.
  • During workflow orchestration that requires session-aware, repeatable calls.

Best practices

  • Always call RUBE_SEARCH_TOOLS first — tool schemas change frequently.
  • Check RUBE_MANAGE_CONNECTIONS shows ACTIVE for the Brex toolkit before any execute call.
  • Pass exact field names and types returned by search results; do not hardcode schemas.
  • Include a memory object (even {}) in RUBE_MULTI_EXECUTE_TOOL calls.
  • Reuse session IDs for a workflow; create new sessions for distinct workflows.
  • Handle pagination tokens in responses and iterate until results are complete.

Example use cases

  • Fetch account balances and recent transactions for daily reconciliation.
  • Initiate a batch of vendor payments using discovered payment tool schema.
  • Generate and export expense reports by calling Composio Brex export tools.
  • Trigger conditional workflows: e.g., if balance < threshold, create funding request.
  • Run a remote workbench job to perform complex multi-step Brex operations atomically.

FAQ

Do I need API keys to use Rube MCP?

No API keys are required for Rube MCP; add https://rube.app/mcp as an MCP server in your client configuration.

What is the first call I must make in every workflow?

Always call RUBE_SEARCH_TOOLS with a Brex-specific use case to retrieve current tool slugs and input schemas before any execution.

What if the Brex connection shows INACTIVE?

Call RUBE_MANAGE_CONNECTIONS for the brex toolkit and follow the provided auth link to complete setup until status is ACTIVE.