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

SKILL

scrapingant-automation

Name: scrapingant-automation
Author: Composio

Automate Scrapingant scraping tasks and workflows through Rube MCP.

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 primarily prompt/documentation for invoking Rube MCP/Composio, with no declared local code execution, embedded secrets, or fixed outbound endpoints. Given its open-source source and strong community adoption, overall risk is low, though actual runtime use still warrants caution around remote MCP data egress and third-party authorization scope.

CredentialsCaution

The material says 'No API keys needed,' but the README explicitly requires activating a `scrapingant` connection via `RUBE_MANAGE_CONNECTIONS` and completing an auth-link flow, indicating likely third-party account authorization or connection tokens in practice; no evidence shows the skill itself stores secrets.

Network egressCaution

The description instructs users to add the remote MCP endpoint `https://rube.app/mcp` and execute tools through Composio/Scrapingant, meaning task inputs and execution arguments may be sent to those declared third-party services. The material does not indicate suspicious outbound destinations beyond Rube/Composio/Scrapingant.

Code executionLow risk

Based on the material, this is a prompt-only usage guide and does not declare downloads, installation, local process spawning, or shell/script execution capabilities; any execution would depend on external MCP/tools rather than the skill text itself.

Data accessCaution

The skill does not declare direct local file or system access, but it does route user-provided task content, tool arguments, and session information through a remote MCP/toolchain. The material does not show requests for local data permissions beyond the stated 'Scrapingant automation' scope.

Supply chainLow risk

The source is an open-source GitHub repository with high community adoption (64.7k stars), both of which are strong risk-reducing signals. The material appears to be a skill entry within `awesome-claude-skills`, though the license is undeclared and maintenance status is unknown, so users should still verify consistency with the repository and upstream Composio docs before use.

Recommendations

Treat this skill as a prompt template rather than a standalone auditable program; separately review Rube MCP and Scrapingant/Composio permissions and privacy terms before production use.
When connecting third-party accounts, prefer least-privilege scopes and dedicated test accounts, and avoid granting access unrelated to scraping tasks.
Do not include unnecessary sensitive data in `RUBE_SEARCH_TOOLS` or `RUBE_MULTI_EXECUTE_TOOL` arguments.
Verify the actual MCP endpoint and OAuth/authorization redirect domains to avoid lookalike or substituted services.

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

// download

Download SKILL.mdInstall manifest ↗

// docs

Scrapingant Automation via Rube MCP

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

Toolkit docs: composio.dev/toolkits/scrapingant

Prerequisites

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

Step 2: Check Connection

RUBE_MANAGE_CONNECTIONS
toolkits: ["scrapingant"]
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 Scrapingant-specific use case
Connect	`RUBE_MANAGE_CONNECTIONS` with toolkit `scrapingant`
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 Autom workflows via Rube MCP while checking current tool schemas first.

ComposioGet→

$ loading_