scrapegraph-ai-automation
Scannednpx machina-cli add skill ComposioHQ/awesome-claude-skills/scrapegraph-ai-automation --openclawScrapegraph AI Automation via Rube MCP
Automate Scrapegraph AI operations through Composio's Scrapegraph AI toolkit via Rube MCP.
Toolkit docs: composio.dev/toolkits/scrapegraph_ai
Prerequisites
- Rube MCP must be connected (RUBE_SEARCH_TOOLS available)
- Active Scrapegraph AI connection via
RUBE_MANAGE_CONNECTIONSwith toolkitscrapegraph_ai - Always call
RUBE_SEARCH_TOOLSfirst 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 ā just add the endpoint and it works.
- Verify Rube MCP is available by confirming
RUBE_SEARCH_TOOLSresponds - Call
RUBE_MANAGE_CONNECTIONSwith toolkitscrapegraph_ai - 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: "Scrapegraph AI 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 Scrapegraph AI task"}]
session: {id: "existing_session_id"}
Step 2: Check Connection
RUBE_MANAGE_CONNECTIONS
toolkits: ["scrapegraph_ai"]
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_CONNECTIONSshows ACTIVE status before executing tools - Schema compliance: Use exact field names and types from the search results
- Memory parameter: Always include
memoryinRUBE_MULTI_EXECUTE_TOOLcalls, 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 Scrapegraph AI-specific use case |
| Connect | RUBE_MANAGE_CONNECTIONS with toolkit scrapegraph_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
Source
git clone https://github.com/ComposioHQ/awesome-claude-skills/blob/master/composio-skills/scrapegraph-ai-automation/SKILL.mdView on GitHub Overview
This skill automates Scrapegraph AI operations through Composio's Scrapegraph AI toolkit via Rube MCP. It emphasizes always searching for current tool schemas with RUBE_SEARCH_TOOLS before execution and ensures connections are ACTIVE and schema-compliant. Practical setup, discovery, and execution flows are designed to minimize manual tooling changes.
How This Skill Works
Configure an MCP endpoint for Rube MCP, verify tool availability with RUBE_SEARCH_TOOLS, and manage your Scrapegraph AI connection with RUBE_MANAGE_CONNECTIONS. Then execute discovered tools using RUBE_MULTI_EXECUTE_TOOL with the correct memory payload and session management to complete workflows.
When to Use It
- When starting a new Scrapegraph AI workflow and you need to discover available tools before running.
- When you must ensure the RUBE MCP connection is ACTIVE before executing tools.
- When you need to run a discovered tool with schema-compliant arguments using RUBE_MULTI_EXECUTE_TOOL.
- When tool schemas change and you should avoid hardcoding slugs or arguments.
- When handling multiple tools in a single session, including pagination and memory management.
Quick Start
- Step 1: Add https://rube.app/mcp as an MCP server in your client configuration and ensure RUBE_SEARCH_TOOLS responds.
- Step 2: Use RUBE_MANAGE_CONNECTIONS with toolkits: ["scrapegraph_ai"] and verify the connection becomes ACTIVE.
- Step 3: Discover tools via RUBE_SEARCH_TOOLS, then run a selected tool with RUBE_MULTI_EXECUTE_TOOL using the memory parameter.
Best Practices
- Always call RUBE_SEARCH_TOOLS before running any workflow to get current tool schemas.
- Verify RUBE_MANAGE_CONNECTIONS shows ACTIVE before executing tools.
- Use exact field names and types from the search results; avoid hardcoding slugs.
- Always include memory in RUBE_MULTI_EXECUTE_TOOL calls, even if empty ({}).
- Reuse session IDs within a workflow and generate new ones only for separate workflows.
Example Use Cases
- Discover a Scrapegraph AI operation tool, select its slug from RUBE_SEARCH_TOOLS, and run it with a memory payload in a single session.
- Reconnect to Scrapegraph AI via RUBE_MANAGE_CONNECTIONS and confirm ACTIVE status before subsequent tool executions.
- Handle a multi-tool Scrapegraph AI task by discovering tools, validating schemas, and executing with RUBE_MULTI_EXECUTE_TOOL across tools in one workflow.
- Adapt to schema changes by re-running RUBE_SEARCH_TOOLS to fetch updated tool slugs and input schemas.
- Perform bulk tool operations using RUBE_REMOTE_WORKBENCH with run_composio_tool() for Scrapegraph AI tasks.
