Do I need API keys to use Extracta AI automation via Rube MCP?

No. The MCP endpoint at https://rube.app/mcp enables automation without API keys; you just add the endpoint in your client.

How do I verify the connection is ACTIVE?

Use RUBE_MANAGE_CONNECTIONS with toolkit 'extracta_ai' and check that the status is ACTIVE before executing tools.

Why must I always call RUBE_SEARCH_TOOLS before running a tool?

Tool schemas change frequently. RUBE_SEARCH_TOOLS fetches the current tool slugs and required arguments; don’t hardcode slugs or schemas.

extracta-ai-automation

Scanned

npx machina-cli add skill ComposioHQ/awesome-claude-skills/extracta-ai-automation --openclaw

Files (1)

SKILL.md

2.9 KB

Extracta AI Automation via Rube MCP

Automate Extracta AI operations through Composio's Extracta AI toolkit via Rube MCP.

Toolkit docs: composio.dev/toolkits/extracta_ai

Prerequisites

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

Step 2: Check Connection

RUBE_MANAGE_CONNECTIONS
toolkits: ["extracta_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_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 Extracta AI-specific use case
Connect	`RUBE_MANAGE_CONNECTIONS` with toolkit `extracta_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/extracta-ai-automation/SKILL.md

View on GitHub

Overview

Automate Extracta AI operations through Composio's Extracta AI toolkit via Rube MCP. Always search tools first to fetch current schemas, and ensure your Extracta AI connection is active before running workflows. This keeps automation aligned with the latest tool definitions.

How This Skill Works

The workflow uses Rube MCP to discover available Extracta AI tool schemas, then checks that the Extracta AI connection is ACTIVE. Once a tool slug and required arguments are identified from the discovery results, it invokes the tool with RUBE_MULTI_EXECUTE_TOOL, including a memory object, and uses the session from the discovery step to maintain context.

When to Use It

Starting a new Extracta AI automation with Rube MCP
When tool schemas change and you must fetch the latest docs
When validating and reusing an existing session for a workflow
When performing a batch/bulk Extracta AI task with multiple tools
During troubleshooting to ensure the connection is ACTIVE before execution

Quick Start

Step 1: Add https://rube.app/mcp as an MCP server in your client configuration and verify RUBE_SEARCH_TOOLS responds
Step 2: Call RUBE_SEARCH_TOOLS with your Extracta AI use case to obtain tool_slugs and input schemas
Step 3: Call RUBE_MANAGE_CONNECTIONS (toolkit: extracta_ai) to activate the connection, then run RUBE_MULTI_EXECUTE_TOOL with a discovered tool slug and memory

Best Practices

Always call RUBE_SEARCH_TOOLS before executing any workflow to get current tool slugs and schemas
Verify RUBE_MANAGE_CONNECTIONS shows ACTIVE status prior to tool execution
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 handle pagination tokens when they appear

Example Use Cases

Automate a document extraction task by discovering the Extracta AI tools, selecting the relevant slug, and executing with the required arguments and memory
Update an automation after a tool schema changes by re-running RUBE_SEARCH_TOOLS to pull the new schema and adjusting the tool slug
Run a multi-tool sequence to process a batch of documents, carrying memory across steps via RUBE_MULTI_EXECUTE_TOOL
Perform bulk operations using RUBE_REMOTE_WORKBENCH and run_composio_tool() for scalable workflows
Re-establish a dropped connection with RUBE_MANAGE_CONNECTIONS and then resume automation once status ACTIVE

Frequently Asked Questions

Add this skill to your agents