Why must I call RUBE_SEARCH_TOOLS first?

Tool schemas change over time. Searching first ensures you use current tool slugs and expected input structures.

What is the memory parameter in RUBE_MULTI_EXECUTE_TOOL?

Memory is a payload you pass through the tool call to maintain state. Include memory: {} if there is no data to preserve.

ninox-automation

Scanned

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

Files (1)

SKILL.md

2.8 KB

Ninox Automation via Rube MCP

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

Toolkit docs: composio.dev/toolkits/ninox

Prerequisites

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

Step 2: Check Connection

RUBE_MANAGE_CONNECTIONS
toolkits: ["ninox"]
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 Ninox-specific use case
Connect	`RUBE_MANAGE_CONNECTIONS` with toolkit `ninox`
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/ninox-automation/SKILL.mdView on GitHub

Overview

Automate Ninox operations through Composio's Ninox toolkit using Rube MCP. Always search for current tool schemas first to adapt to changes. This enables discovering tools, managing connections, and executing Ninox tasks with structured inputs.

How This Skill Works

Connect Rube MCP and Ninox, then call RUBE_SEARCH_TOOLS to retrieve available tool slugs and schemas. Use RUBE_MANAGE_CONNECTIONS to verify the Ninox connection is ACTIVE, then execute tools with RUBE_MULTI_EXECUTE_TOOL, supplying the discovered tool_slug, schema-compliant arguments, a memory object, and a session_id. Always reference live schemas and avoid hardcoding tool slugs.

When to Use It

Automate creating Ninox records from external CRM or form submissions
Bulk update Ninox records based on events from another system
Validate and transform data by running Ninox tools with current schemas
Bulk archive or delete Ninox records according to external criteria
Synchronize Ninox data with external datasets on a schedule

Quick Start

Step 1: RUBE_SEARCH_TOOLS to fetch Ninox tool slugs and input schemas
Step 2: RUBE_MANAGE_CONNECTIONS with toolkits: ["ninox"] and confirm ACTIVE
Step 3: RUBE_MULTI_EXECUTE_TOOL with a discovered tool_slug, proper arguments, memory, and session_id

Best Practices

Always call RUBE_SEARCH_TOOLS first to obtain current tool schemas
Verify RUBE_MANAGE_CONNECTIONS shows ACTIVE before executing tools
Use exact field names and types from the search results; avoid hardcoding
Include memory in RUBE_MULTI_EXECUTE_TOOL calls, even if empty ({})
Reuse session IDs within a workflow and handle pagination if provided

Example Use Cases

Create a new Ninox record from a lead form captured in an external CRM
Update Ninox task records in bulk when project status changes in a separate tool
Archive closed opportunities in Ninox based on criteria from another system
Sync Ninox inventory records with an external ERP feed on a daily schedule
Query Ninox for records meeting specific criteria and generate a report in another app

Frequently Asked Questions

Add this skill to your agents