Skip to main content
NEW · APP STORE Now on iOS · macOS · iPad Android & Windows soon GET IT
Prompts Browserhub Rube MCP Automation Guide

agent tool_use skill risk: low

Browserhub Rube MCP Automation Guide

Provides instructions for automating Browserhub operations via Composio's Rube MCP, including prerequisites, connection setup with RUBE_MANAGE_CONNECTIONS, tool discovery using RUB…

  • External action: high

SKILL 1 file

SKILL.md
---
name: browserhub-automation
description: "Automate Browserhub tasks via Rube MCP (Composio). Always search tools first for current schemas."
---
# Browserhub Automation via Rube MCP

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

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

## Prerequisites

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

### Step 2: Check Connection

```
RUBE_MANAGE_CONNECTIONS
toolkits: ["browserhub"]
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 Browserhub-specific use case |
| Connect | `RUBE_MANAGE_CONNECTIONS` with toolkit `browserhub` |
| 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)*

REQUIRED CONTEXT

  • RUBE_SEARCH_TOOLS availability
  • active browserhub connection

OPTIONAL CONTEXT

  • existing session_id

TOOLS REQUIRED

  • RUBE_SEARCH_TOOLS
  • RUBE_MANAGE_CONNECTIONS
  • RUBE_MULTI_EXECUTE_TOOL

ROLES & RULES

  1. Always call `RUBE_SEARCH_TOOLS` first to get current tool schemas
  2. Always discover available tools before executing workflows
  3. Verify Rube MCP is available by confirming `RUBE_SEARCH_TOOLS` responds
  4. Call `RUBE_MANAGE_CONNECTIONS` with toolkit `browserhub`
  5. Confirm connection status shows ACTIVE before running any workflows
  6. Never hardcode tool slugs or arguments without calling `RUBE_SEARCH_TOOLS`
  7. Verify `RUBE_MANAGE_CONNECTIONS` shows ACTIVE status before executing tools
  8. Use exact field names and types from the search results
  9. Always include `memory` in `RUBE_MULTI_EXECUTE_TOOL` calls, even if empty
  10. Reuse session IDs within a workflow
  11. Generate new session IDs for new workflows
  12. Check responses for pagination tokens and continue fetching until complete

EXPECTED OUTPUT

Format
markdown
Constraints
  • always search tools first
  • verify active connection before execution
  • reuse session ids

SUCCESS CRITERIA

  • Always search tools first for current schemas
  • Verify connection is ACTIVE before executing tools
  • Use schema-compliant arguments from search results

FAILURE MODES

  • May hardcode tool slugs or arguments without searching first
  • May skip connection status verification
  • May omit the memory parameter in execute calls
  • May fail to reuse or correctly manage session IDs

EXAMPLES

Includes multiple example RUBE tool calls (RUBE_SEARCH_TOOLS, RUBE_MANAGE_CONNECTIONS, RUBE_MULTI_EXECUTE_TOOL) with sample arguments and session handling.

CAVEATS

Dependencies
  • Requires Rube MCP connected (RUBE_SEARCH_TOOLS available)
  • Requires active Browserhub connection via RUBE_MANAGE_CONNECTIONS
Missing context
  • Concrete examples of Browserhub use cases or tool slugs
  • Error handling or retry strategy when tool calls fail
Ambiguities
  • Placeholder text 'your specific Browserhub task' is not accompanied by examples
  • Does not define what values or structure 'memory' should contain beyond being present

QUALITY

OVERALL
0.76
CLARITY
0.78
SPECIFICITY
0.82
REUSABILITY
0.75
COMPLETENESS
0.72

IMPROVEMENT SUGGESTIONS

  • Replace the generic placeholder with 2-3 concrete example use cases and corresponding RUBE_SEARCH_TOOLS queries
  • Add a short 'Error handling' subsection describing how to respond to non-ACTIVE connection status or schema validation errors

USAGE

Copy the prompt above and paste it into your AI of choice — Claude, ChatGPT, Gemini, or anywhere else you're working. Replace any placeholder sections with your own context, then ask for the output.

MORE FOR AGENT