What is required to use brex-automation?

Rube MCP must be connected, a Brex connection must be ACTIVE, and you must always call RUBE_SEARCH_TOOLS to fetch current tool schemas.

Why must I include memory in RUBE_MULTI_EXECUTE_TOOL calls?

Memory is required to maintain state across tool executions; even if empty, include {}.

How do I ensure tool schemas are up to date?

Always perform RUBE_SEARCH_TOOLS before executing; tool slugs and argument fields can change.

brex-automation

Scanned

npx machina-cli add skill ComposioHQ/awesome-claude-skills/brex-automation --openclaw

Files (1)

SKILL.md

2.8 KB

Brex Automation via Rube MCP

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

Toolkit docs: 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.

Verify Rube MCP is available by confirming RUBE_SEARCH_TOOLS responds
Call RUBE_MANAGE_CONNECTIONS with toolkit brex
If connection is not ACTIVE, follow the returned auth link to complete setup
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

Source

git clone https://github.com/ComposioHQ/awesome-claude-skills/blob/master/composio-skills/brex-automation/SKILL.mdView on GitHub

Overview

Automate Brex operations using Composio Brex toolkit via Rube MCP. Always fetch current tool schemas with RUBE_SEARCH_TOOLS and verify an ACTIVE Brex connection before running workflows for up-to-date, safe automation.

How This Skill Works

Connect to Rube MCP and the Brex toolkit, then query available Brex tools with RUBE_SEARCH_TOOLS to obtain current tool slugs and input schemas. Pick a tool slug, prepare arguments that match the schema, and execute with RUBE_MULTI_EXECUTE_TOOL, including a memory object and a session_id. Always use the latest schemas and avoid hardcoding slugs or argument names.

When to Use It

When you need to automate a routine Brex task such as an expense workflow or report export.
When tool schemas have changed and you must fetch latest slugs and argument definitions before running.
When building a multi-step Brex workflow that reuses a session across steps.
When performing bulk or batch Brex operations using remote bench execution.
When ensuring the Brex connection is ACTIVE before executing any tools.

Quick Start

Step 1: Ensure Rube MCP is connected and RUBE_SEARCH_TOOLS responds.
Step 2: Discover available Brex tools with RUBE_SEARCH_TOOLS using a Brex use_case.
Step 3: Select a tool_slug, prepare arguments, and call RUBE_MULTI_EXECUTE_TOOL with memory and a session_id.

Best Practices

Always call RUBE_SEARCH_TOOLS before executing to get current schemas.
Check RUBE_MANAGE_CONNECTIONS for ACTIVE status before running tools.
Use exact field names and types from the search results; avoid guessing.
Include memory in every RUBE_MULTI_EXECUTE_TOOL call, even if empty.
Reuse session IDs within a workflow and generate new ones for new workflows.

Example Use Cases

Discover Brex tools for month-end expenses with RUBE_SEARCH_TOOLS, then run the export tool in a session to generate a report.
Establish a Brex connection with RUBE_MANAGE_CONNECTIONS, verify ACTIVE, then execute a tool to fetch current balances.
Fetch up-to-date tool schemas via RUBE_GET_TOOL_SCHEMAS and run a tool with the latest definitions.
Perform bulk Brex operations by using RUBE_REMOTE_WORKBENCH to run multiple tools in one batch.
Reuse a session_id across a sequence of Brex tasks to maintain context and avoid re-authentication.

Frequently Asked Questions

Add this skill to your agents