$ ~/registry/skill/composiohq-composio-skills-scrape-do-automation

SKILL

scrape-do-automation

Name: scrape-do-automation
Author: Composio

Automate Scrape Do workflows via Rube MCP to collect structured web data.

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 prompt-only and open-source, with no direct local secret requirement or local code execution in the provided material. Its main security consideration is that it instructs users to connect to a remote Rube MCP and operate external Composio scrape_do tooling, so the caution lies in downstream remote-tool use and data egress boundaries rather than the skill text itself.

CredentialsCaution

The material says no API key is needed to add Rube MCP, but it also requires activating a `scrape_do` connection via `RUBE_MANAGE_CONNECTIONS` and completing an auth link, which implies downstream account authorization or tokens may still be involved. The skill does not directly collect secrets, but users should watch the third-party access granted during the remote connection flow.

Network egressCaution

It explicitly instructs users to add the remote MCP endpoint `https://rube.app/mcp` and perform actions through Composio/Scrape Do tooling. `RUBE_SEARCH_TOOLS`, `RUBE_MANAGE_CONNECTIONS`, and `RUBE_MULTI_EXECUTE_TOOL` all imply that task content, arguments, and possibly target data will be sent to the declared remote services. No suspicious unrelated endpoint is shown, but normal third-party data egress is present.

Code executionLow risk

Based on the provided material, this is a prompt/README-style skill with no executable script, install command, or local process-launch instruction, and it does not claim direct local system access. Any execution capability appears to reside in the remote MCP/tool side rather than in the skill itself.

Data accessCaution

The skill documentation does not state that it reads local files or accesses local machine resources. However, it is meant to automate Scrape Do operations through remote tools, so actual data access will depend on user-supplied arguments, the permissions of the authenticated scrape_do account, and the remote tool schema. No obvious excessive local authorization is requested, but remote data-handling scope should be verified.

Supply chainLow risk

The source is an open GitHub repository with very strong community adoption (~64.7k stars), which materially lowers supply-chain risk. The current material is auditable prompt/documentation content rather than a closed-source binary; while the license is not stated and maintenance status is unknown, the available evidence points to relatively low supply-chain risk.

Recommendations

Before adding `https://rube.app/mcp`, verify what prompts, parameters, and result data your client will send to the MCP server.
When completing the `scrape_do` authorization flow, review the exact permissions requested and avoid granting unnecessary access.
Provide only the minimum data needed to the remote tools; do not send sensitive credentials, personal data, or internal page content unless necessary.
Review Composio's scrape_do toolkit documentation and schemas before production use to confirm behavior, logging, and data flows.

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

// download

Download SKILL.mdInstall manifest ↗

// docs

Scrape Do Automation via Rube MCP

Automate Scrape Do operations through Composio's Scrape Do toolkit via Rube MCP.

Toolkit docs: composio.dev/toolkits/scrape_do

Prerequisites

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

Step 2: Check Connection

RUBE_MANAGE_CONNECTIONS
toolkits: ["scrape_do"]
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 Scrape Do-specific use case
Connect	`RUBE_MANAGE_CONNECTIONS` with toolkit `scrape_do`
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 Moz SEO tasks via Rube MCP using current tool schemas first.

ComposioGet→

$ loading_