$ ~/registry/skill/composiohq-composio-skills-bouncer-automation

SKILL

bouncer-automation

Name: bouncer-automation
Author: Composio

Automate Bouncer tasks through Rube MCP after checking current tool schemas.

Stars

★ 67,763

Source

GitHub

Updated

2026-07-15

// securityCaution

Prompt only, no code
Open source
Community-trusted· 64.7k

Summary

This skill appears to be an open-source prompt-only wrapper with strong community credibility, and it does not show local code execution or direct local data access. The main security consideration is its reliance on the remote Rube MCP/Composio service and an external Bouncer authorization flow, so network egress and third-party connection handling should be treated with caution.

CredentialsCaution

The material states the skill itself does not require local API keys or environment variables, but actual use requires establishing a `bouncer` connection via `RUBE_MANAGE_CONNECTIONS` and completing authentication through a returned auth link. This implies normal third-party credential delegation/handling through Rube/Composio, with typical caution around account linking and token management.

Network egressCaution

The README explicitly requires adding the remote MCP endpoint `https://rube.app/mcp` and using Composio/Rube to discover and execute Bouncer tools. Therefore, task inputs, session IDs, tool arguments, and potentially business data will be sent to a declared third-party service. The endpoint is disclosed and functionally related, but this is still explicit external data egress.

Code executionLow risk

Based on the provided material, this is a prompt/instructional skill and does not include executable install scripts, binaries, shell commands, or requirements to start local processes. The skill itself does not show direct code execution capability.

Data accessLow risk

The material does not declare any need to read or write local files, system directories, clipboard contents, databases, or other local resources. Its data access scope is primarily remote interaction with Bouncer-related resources rather than overbroad local access.

Supply chainLow risk

This item is marked as `prompt-only` and `open-source`, and it comes from a GitHub repository with high community adoption (64.7k stars), making it substantially more auditable than closed-source distributions. Although the license is unspecified and maintenance status is unknown, these do not by themselves constitute a high-risk red flag; overall supply-chain risk is low.

Recommendations

Only connect a Bouncer account after confirming you trust `rube.app`/Composio as a third-party intermediary, and prefer least-privilege authorization.
Avoid sending unnecessary sensitive business data in task arguments, since it should be assumed to transit the remote MCP service.
On first use, verify the auth page domain, requested scopes, and linked account to avoid authorizing the wrong tenant or environment.
If your organization has compliance requirements, further verify the service's data handling, logging retention, and license/maintenance status.

Audited by: gpt-5.4 · 2026-06-17

// install

Copy the install command and let the AI configure it · recommended for beginners

Please install the "bouncer-automation" skill from askskill:
1. Download https://raw.githubusercontent.com/ComposioHQ/awesome-claude-skills/master/composio-skills/bouncer-automation/SKILL.md
2. Save it as ~/.claude/skills/bouncer-automation/SKILL.md
3. Reload skills and tell me it's ready

// download

Download SKILL.mdInstall manifest ↗

// docs

Bouncer Automation via Rube MCP

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

Toolkit docs: composio.dev/toolkits/bouncer

Prerequisites

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

Step 2: Check Connection

RUBE_MANAGE_CONNECTIONS
toolkits: ["bouncer"]
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 Bouncer-specific use case
Connect	`RUBE_MANAGE_CONNECTIONS` with toolkit `bouncer`
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

Automate Bonsai tasks via Rube MCP using current tool schemas first.

ComposioGet→

$ loading_