home / skills / composiohq / awesome-claude-skills / browser-tool-automation

browser-tool-automation skill

/browser-tool-automation

This skill automates browser tool tasks using Rube MCP and Composio, ensuring current tool schemas are fetched before execution.

npx playbooks add skill composiohq/awesome-claude-skills --skill browser-tool-automation

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

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

# Browser Tool Automation via Rube MCP

Automate Browser Tool operations through Composio's Browser Tool toolkit via Rube MCP.

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

## Prerequisites

- Rube MCP must be connected (RUBE_SEARCH_TOOLS available)
- Active Browser Tool connection via `RUBE_MANAGE_CONNECTIONS` with toolkit `browser_tool`
- 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 `browser_tool`
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: "Browser Tool 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 Browser Tool task"}]
session: {id: "existing_session_id"}
```

### Step 2: Check Connection

```
RUBE_MANAGE_CONNECTIONS
toolkits: ["browser_tool"]
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 Browser Tool-specific use case |
| Connect | `RUBE_MANAGE_CONNECTIONS` with toolkit `browser_tool` |
| 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 Browser Tool tasks through Rube MCP (Composio) to run browser-based actions reliably from agent workflows. It guides discovery, connection management, and execution of Composio Browser Tool operations while enforcing schema compliance and safe session handling.

How this skill works

The skill first calls RUBE_SEARCH_TOOLS to discover current tool slugs, input schemas, and recommended execution plans. It then verifies or establishes a Browser Tool connection via RUBE_MANAGE_CONNECTIONS and executes actions using RUBE_MULTI_EXECUTE_TOOL (including a memory object and session_id). It supports pagination, session reuse, and fetching full schemas via RUBE_GET_TOOL_SCHEMAS or bulk runs via RUBE_REMOTE_WORKBENCH.

When to use it

  • Automating browser interactions (scraping, form fills, navigation) from an AI agent
  • Orchestrating multi-step web workflows that require up-to-date tool schemas
  • Running batch or parallel browser tasks with Composio toolkits
  • Integrating browser-based actions into larger Rube MCP workflows or pipelines

Best practices

  • Always call RUBE_SEARCH_TOOLS before using any tool to fetch current slugs and input schemas
  • Confirm Browser Tool connection status with RUBE_MANAGE_CONNECTIONS and follow returned auth links until status is ACTIVE
  • Pass memory (even if empty) in RUBE_MULTI_EXECUTE_TOOL calls and reuse session_id within a workflow
  • Use exact field names and types from the returned schema; do not hardcode argument shapes
  • Handle pagination tokens in search responses and iterate until results are complete

Example use cases

  • Discover available browser automation actions, then run a targeted click-and-scrape sequence using the discovered tool slug
  • Connect a new user browser session via the returned auth link and verify ACTIVE status before executing scripted navigation
  • Batch-run link checks and screenshot captures across many pages using RUBE_MULTI_EXECUTE_TOOL with memory and session reuse
  • Fetch full tool schemas with RUBE_GET_TOOL_SCHEMAS to validate payloads programmatically before execution
  • Execute complex, multi-tool browser workflows from a remote workbench using RUBE_REMOTE_WORKBENCH and run_composio_tool()

FAQ

Do I need API keys to use Rube MCP?

No API keys are required when adding https://rube.app/mcp as an MCP server; the endpoint works once configured in your client.

What if a tool schema changes mid-workflow?

Always re-run RUBE_SEARCH_TOOLS at key workflow boundaries. If schemas change, adapt arguments accordingly and revalidate before executing.