What is required to use onedesk-automation?

A connected Rube MCP (RUBE_SEARCH_TOOLS available) and an active Onedesk connection via the Onedesk toolkit. Always search for current tool schemas before execution.

Why must I search tools first?

Tool schemas change over time. Re-searching ensures you use correct slugs and argument names without hardcoding.

What should be included in tool executions?

Include memory in RUBE_MULTI_EXECUTE_TOOL calls, even if empty ({}), and reuse session IDs within a workflow while ensuring the connection remains ACTIVE.

onedesk-automation

Scanned

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

Files (1)

SKILL.md

2.9 KB

Onedesk Automation via Rube MCP

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

Toolkit docs: composio.dev/toolkits/onedesk

Prerequisites

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

Step 2: Check Connection

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

Overview

Automates Onedesk operations through Composio's Onedesk toolkit via Rube MCP. It emphasizes always discovering current tool schemas before execution and ensures a proper connection is established prior to running workflows.

How This Skill Works

The workflow starts by discovering available Onedesk tools with RUBE_SEARCH_TOOLS, then verifies the Onedesk connection via RUBE_MANAGE_CONNECTIONS, and finally executes the chosen tool using RUBE_MULTI_EXECUTE_TOOL with a memory payload and a session_id. This sequence prevents hardcoding tool slugs and adapts to schema changes in real time.

When to Use It

When setting up a new Onedesk workflow: discover tools and establish a connection before execution.
When you need to execute a specific Onedesk task after obtaining tool_slug and required arguments.
When Onedesk tool schemas may have changed: re-run RUBE_SEARCH_TOOLS to fetch current input schemas.
When running multiple Onedesk tools in a single automation workflow using a shared session.
When troubleshooting: verify ACTIVE connection status and ensure memory is included in tool executions.

Quick Start

Step 1: Add https://rube.app/mcp as an MCP server and confirm RUBE_SEARCH_TOOLS responds.
Step 2: Call RUBE_MANAGE_CONNECTIONS with toolkit: ["onedesk"] and ensure the session shows ACTIVE.
Step 3: Use RUBE_SEARCH_TOOLS to discover tools, then execute a tool with RUBE_MULTI_EXECUTE_TOOL using the discovered slug and proper arguments (include memory and session_id).

Best Practices

Always call RUBE_SEARCH_TOOLS first to fetch current tool schemas and avoid hardcoding slugs or fields.
Check that RUBE_MANAGE_CONNECTIONS reports ACTIVE before executing any tools.
Use exact field names and types from the search results to ensure schema compliance.
Include memory in every RUBE_MULTI_EXECUTE_TOOL call, even if empty ({}).
Reuse session IDs within a workflow and generate new IDs for new workflows; monitor for pagination in tool lists.

Example Use Cases

Discover Onedesk tools for a specified use case, then execute a matched TOOL_SLUG with required arguments.
Connect to Onedesk via Rube MCP, verify ACTIVE status, and run a ticket-creation workflow using discovered schemas.
Fetch current schemas, then submit a tool call to update a ticket using the exact argument names from the search results.
Run a sequence of Onedesk operations (e.g., create, update, fetch status) within a single session using RUBE_MULTI_EXECUTE_TOOL.
Use RUBE_REMOTE_WORKBENCH to batch-run multiple composio tools for Onedesk in a bulk operation.

Frequently Asked Questions

Add this skill to your agents