Do I need API keys to use OCR Web Service automation?

No API keys are required. Add the MCP server at rube.app/mcp and use the provided RUBE commands.

What if tool slugs change?

Always fetch current tool slugs and schemas with RUBE_SEARCH_TOOLS before executing anything.

How can I ensure successful execution?

Verify the connection is ACTIVE with RUBE_MANAGE_CONNECTIONS, include memory in RUBE_MULTI_EXECUTE_TOOL calls, and reuse a session_id to maintain state across steps.

ocr-web-service-automation

Scanned

npx machina-cli add skill ComposioHQ/awesome-claude-skills/ocr-web-service-automation --openclaw

Files (1)

SKILL.md

3.0 KB

OCR Web Service Automation via Rube MCP

Automate OCR Web Service operations through Composio's OCR Web Service toolkit via Rube MCP.

Toolkit docs: composio.dev/toolkits/ocr_web_service

Prerequisites

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

Step 2: Check Connection

RUBE_MANAGE_CONNECTIONS
toolkits: ["ocr_web_service"]
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 OCR Web Service-specific use case
Connect	`RUBE_MANAGE_CONNECTIONS` with toolkit `ocr_web_service`
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/ocr-web-service-automation/SKILL.md

View on GitHub

Overview

Automate OCR Web Service operations using Composio's OCR toolkit through Rube MCP. The workflow starts by discovering current tool schemas via RUBE_SEARCH_TOOLS, establishing a working connection with RUBE_MANAGE_CONNECTIONS, and then executing tools with RUBE_MULTI_EXECUTE_TOOL. Keeping schemas fresh and connections ACTIVE ensures reliable OCR tasks.

How This Skill Works

The workflow begins by adding the MCP at rube.app/mcp and verifying availability with RUBE_SEARCH_TOOLS. Next, connect to the OCR toolkit via RUBE_MANAGE_CONNECTIONS and select a tool slug from the discovered schemas. Finally, execute the tool with RUBE_MULTI_EXECUTE_TOOL, passing memory:{} and a session_id to maintain state.

When to Use It

When you need to automate OCR tasks and rely on current tool schemas
To batch OCR jobs in a workflow with session reuse
Before executing any tool, verify RUBE_MANAGE_CONNECTIONS shows ACTIVE
When tool schemas change frequently, always refetch with RUBE_SEARCH_TOOLS
For bulk OCR tasks using RUBE_MULTI_EXECUTE_TOOL or RUBE_REMOTE_WORKBENCH

Quick Start

Step 1: Add MCP endpoint at https://rube.app/mcp and verify availability with RUBE_SEARCH_TOOLS
Step 2: Discover OCR tools using RUBE_SEARCH_TOOLS for your use_case (e.g., OCR Web Service operations)
Step 3: Check ACTIVE connection with RUBE_MANAGE_CONNECTIONS and run a tool via RUBE_MULTI_EXECUTE_TOOL (include memory and a session_id)

Best Practices

Always call RUBE_SEARCH_TOOLS first to fetch current tool schemas
Verify RUBE_MANAGE_CONNECTIONS reports ACTIVE before execution
Use exact field names and types from search results
Include memory:{} in RUBE_MULTI_EXECUTE_TOOL calls
Reuse session IDs within a workflow and fetch pagination until complete

Example Use Cases

Batch OCR on invoices: discover the invoice_ocr tool slug, ensure ACTIVE connection, then execute with a batch of image paths using a single session_id.
Process scanned receipts: fetch the receipt_ocr tool from RUBE_SEARCH_TOOLS, verify connectivity, and run per-receipt arguments in one workflow.
Ingest new document types: search for a doc_ocr tool, confirm ACTIVE, and run multiple documents in a session with RUBE_MULTI_EXECUTE_TOOL.
Bulk archival OCR: use RUBE_REMOTE_WORKBENCH with run_composio_tool to parallelize many OCR tasks across docs.
Pagination-safe fetch: for tools returning paged results, repeatedly call RUBE_SEARCH_TOOLS or related endpoints until tokens are exhausted.

Frequently Asked Questions

Add this skill to your agents