Automate Webscraping AI workflows through Rube MCP with tool discovery.
Copy the install command and let the AI configure it · recommended for beginners
Please install the "webscraping-ai-automation" skill from askskill: 1. Download https://raw.githubusercontent.com/ComposioHQ/awesome-claude-skills/master/composio-skills/webscraping-ai-automation/SKILL.md 2. Save it as ~/.claude/skills/webscraping-ai-automation/SKILL.md 3. Reload skills and tell me it's ready
Developers or researchers can search for currently available tools and parameter definitions before starting a web scraping automation flow, avoiding outdated slugs or fields. This is useful when tool schemas change over time.
When a team runs tasks through Composio's Webscraping AI toolkit, they can first verify that the connection is ACTIVE. If it is not active, the system points them to authorization steps and reduces execution errors.
Within the same workflow, reuse the session ID to discover tools, check the connection, and then execute tools. This follows the documented pattern and helps with pagination or multi-step operations.
The README explains how to automate Webscraping AI tasks through Rube MCP using Composio's toolkit. It covers prerequisites, connection and authorization steps, and the standard workflow: search tools first with RUBE_SEARCH_TOOLS, verify the toolkit connection with RUBE_MANAGE_CONNECTIONS, and execute with RUBE_MULTI_EXECUTE_TOOL. It also highlights pitfalls such as schema changes, required memory fields, session reuse, and pagination handling.
Automate Webscraping AI operations through Composio's Webscraping AI toolkit via Rube MCP.
Toolkit docs: composio.dev/toolkits/webscraping_ai
RUBE_MANAGE_CONNECTIONS with toolkit webscraping_aiRUBE_SEARCH_TOOLS first to get current tool schemasGet 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.
RUBE_SEARCH_TOOLS respondsRUBE_MANAGE_CONNECTIONS with toolkit webscraping_aiAlways discover available tools before executing workflows:
RUBE_SEARCH_TOOLS
queries: [{use_case: "Webscraping AI operations", known_fields: ""}]
session: {generate_id: true}
This returns available tool slugs, input schemas, recommended execution plans, and known pitfalls.
RUBE_SEARCH_TOOLS
queries: [{use_case: "your specific Webscraping AI task"}]
session: {id: "existing_session_id"}
RUBE_MANAGE_CONNECTIONS
toolkits: ["webscraping_ai"]
session_id: "your_session_id"
RUBE_MULTI_EXECUTE_TOOL
tools: [{
tool_slug: "TOOL_SLUG_FROM_SEARCH",
arguments: {/* schema-compliant args from search results */}
}]
memory: {}
session_id: "your_session_id"
RUBE_SEARCH_TOOLSRUBE_MANAGE_CONNECTIONS shows ACTIVE status before executing toolsmemory in RUBE_MULTI_EXECUTE_TOOL calls, even if empty ({})| Operation | Approach |
|---|---|
| Find tools | RUBE_SEARCH_TOOLS with Webscraping AI-specific use case |
| Connect | RUBE_MANAGE_CONNECTIONS with toolkit webscraping_ai |
| 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
It is used to automate web scraping-related operations through Rube MCP with Composio's Webscraping AI toolkit. The docs specifically emphasize searching for tools first, then executing against the latest schema.
You need Rube MCP connected and RUBE_SEARCH_TOOLS available. You also need an active connection for the `webscraping_ai` toolkit through RUBE_MANAGE_CONNECTIONS.
Because tool schemas may change, tool slugs and arguments should not be hardcoded. Calling RUBE_SEARCH_TOOLS first provides the current input structure, recommended execution plans, and known pitfalls.
Automate BunnyCDN configuration, queries, and operational tasks via Rube MCP.
Automate Calendarhero scheduling and meeting tasks through Rube MCP.
Automate Callpage tasks through Rube MCP to improve callback and lead operations.
Automate Melo workflows via Rube MCP using current tool schemas first.
Apply official brand colors and typography to keep artifacts visually consistent.
Automate BuiltWith tech-stack lookups for research, prospecting, and competitive analysis.
Automate ScrapingBee scraping tasks and web data workflows via Rube MCP.
Automate Scrapegraph AI tasks via Rube MCP with schema-first tool discovery.
Automate Scrapingant scraping tasks and workflows through Rube MCP.
Automate BrowseAI workflows to extract web data and monitor page changes.
Automate Scrapfly workflows through Rube MCP with tool discovery and execution.
Automate AI/ML API workflows via Rube MCP, checking latest tool schemas first.