helpdesk-automation
Scannednpx machina-cli add skill davepoon/buildwithclaude/helpdesk-automation --openclawHelpDesk Automation via Rube MCP
Automate HelpDesk ticketing operations through Composio's HelpDesk toolkit via Rube MCP.
Toolkit docs: composio.dev/toolkits/helpdesk
Prerequisites
- Rube MCP must be connected (RUBE_SEARCH_TOOLS available)
- Active HelpDesk connection via
RUBE_MANAGE_CONNECTIONSwith toolkithelpdesk - 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 — just add the endpoint and it works.
- Verify Rube MCP is available by confirming
RUBE_SEARCH_TOOLSresponds - Call
RUBE_MANAGE_CONNECTIONSwith toolkithelpdesk - If connection is not ACTIVE, follow the returned auth link to complete HelpDesk authentication
- Confirm connection status shows ACTIVE before running any workflows
Core Workflows
1. List and Browse Tickets
When to use: User wants to retrieve, browse, or paginate through support tickets
Tool sequence:
HELPDESK_LIST_TICKETS- List tickets with sorting and pagination [Required]
Key parameters:
silo: Ticket folder - 'tickets', 'archive', 'trash', or 'spam' (default: 'tickets')sortBy: Sort field - 'createdAt', 'updatedAt', or 'lastMessageAt' (default: 'createdAt')order: Sort direction - 'asc' or 'desc' (default: 'desc')pageSize: Results per page, 1-100 (default: 20)next.value: Timestamp cursor for forward paginationnext.ID: ID cursor for forward paginationprev.value: Timestamp cursor for backward paginationprev.ID: ID cursor for backward pagination
Pitfalls:
- Pagination uses cursor-based approach with timestamp + ID pairs
- Forward pagination requires both
next.valueandnext.IDfrom previous response - Backward pagination requires both
prev.valueandprev.ID silodetermines which folder to list from; default is active ticketspageSizemax is 100; default is 20- Archived and trashed tickets are in separate silos
2. Manage Ticket Views
When to use: User wants to see saved agent views for organizing tickets
Tool sequence:
HELPDESK_LIST_VIEWS- List all agent views [Required]
Key parameters: (none required)
Pitfalls:
- Views are predefined saved filters configured by agents in the HelpDesk UI
- View definitions include filter criteria that can be used to understand ticket organization
- Views cannot be created or modified via API; they are managed in the HelpDesk UI
3. Use Canned Responses
When to use: User wants to list available canned (template) responses for tickets
Tool sequence:
HELPDESK_LIST_CANNED_RESPONSES- Retrieve all predefined reply templates [Required]
Key parameters: (none required)
Pitfalls:
- Canned responses are predefined templates for common replies
- They may include placeholder variables that need to be filled in
- Canned responses are managed through the HelpDesk UI
- Response content may include HTML formatting
4. Inspect Custom Fields
When to use: User wants to view custom field definitions for the account
Tool sequence:
HELPDESK_LIST_CUSTOM_FIELDS- List all custom field definitions [Required]
Key parameters: (none required)
Pitfalls:
- Custom fields extend the default ticket schema with organization-specific data
- Field definitions include field type, name, and validation rules
- Custom fields are configured in the HelpDesk admin panel
- Field values appear on tickets when the field has been populated
Common Patterns
Ticket Browsing Pattern
1. Call HELPDESK_LIST_TICKETS with desired silo and sortBy
2. Process the returned page of tickets
3. Extract next.value and next.ID from the response
4. Call HELPDESK_LIST_TICKETS with those cursor values for next page
5. Continue until no more cursor values are returned
Ticket Folder Navigation
Active tickets: silo='tickets'
Archived: silo='archive'
Trashed: silo='trash'
Spam: silo='spam'
Cursor-Based Pagination
Forward pagination:
- Use next.value (timestamp) and next.ID from response
- Pass as next.value and next.ID parameters in next call
Backward pagination:
- Use prev.value (timestamp) and prev.ID from response
- Pass as prev.value and prev.ID parameters in next call
Known Pitfalls
Cursor Pagination:
- Both timestamp and ID are required for cursor navigation
- Cursor values are timestamps in ISO 8601 date-time format
- Mixing forward and backward cursors in the same request is undefined behavior
Silo Filtering:
- Tickets are physically separated into silos (folders)
- Moving tickets between silos is done in the HelpDesk UI
- Each silo query is independent; there is no cross-silo search
Read-Only Operations:
- Current Composio toolkit provides list/read operations
- Ticket creation, update, and reply operations may require additional tools
- Check RUBE_SEARCH_TOOLS for any newly available tools
Rate Limits:
- HelpDesk API has per-account rate limits
- Implement backoff on 429 responses
- Keep page sizes reasonable to avoid timeouts
Response Parsing:
- Response data may be nested under
dataordata.data - Parse defensively with fallback patterns
- Ticket IDs are strings
Quick Reference
| Task | Tool Slug | Key Params |
|---|---|---|
| List tickets | HELPDESK_LIST_TICKETS | silo, sortBy, order, pageSize |
| List views | HELPDESK_LIST_VIEWS | (none) |
| List canned responses | HELPDESK_LIST_CANNED_RESPONSES | (none) |
| List custom fields | HELPDESK_LIST_CUSTOM_FIELDS | (none) |
Powered by Composio
Source
git clone https://github.com/davepoon/buildwithclaude/blob/main/plugins/all-skills/skills/helpdesk-automation/SKILL.mdView on GitHub Overview
Automate HelpDesk ticketing operations using Composio's HelpDesk toolkit through Rube MCP. This skill covers listing tickets, managing agent views, using canned responses, and inspecting custom fields. Always query RUBE_SEARCH_TOOLS first to fetch current schemas before any workflow.
How This Skill Works
First, verify Rube MCP is connected and fetch current tool schemas with RUBE_SEARCH_TOOLS. Then establish a HelpDesk connection with RUBE_MANAGE_CONNECTIONS (toolkit 'helpdesk') and ensure the connection is ACTIVE. Core workflows call specific tools such as HELPDESK_LIST_TICKETS, HELPDESK_LIST_VIEWS, HELPDESK_LIST_CANNED_RESPONSES, and HELPDESK_LIST_CUSTOM_FIELDS to perform operations.
When to Use It
- Retrieve, browse, or paginate through tickets across silos using HELPDESK_LIST_TICKETS with appropriate sorting and pageSize.
- Review saved agent views to understand preconfigured filters and organize ticket workflows using HELPDESK_LIST_VIEWS.
- List available canned responses to respond quickly to tickets using HELPDESK_LIST_CANNED_RESPONSES.
- Inspect custom field definitions to extend or validate ticket data using HELPDESK_LIST_CUSTOM_FIELDS.
- Verify setup and connection status before running any workflows and ensure current tool schemas are loaded.
Quick Start
- Step 1: Verify Rube MCP readiness by calling RUBE_SEARCH_TOOLS.
- Step 2: Connect to HelpDesk with RUBE_MANAGE_CONNECTIONS, toolkit 'helpdesk', and complete any required auth.
- Step 3: Run a core workflow, e.g. HELPDESK_LIST_TICKETS with your desired parameters (silo, sortBy, pageSize).
Best Practices
- Always call RUBE_SEARCH_TOOLS first to fetch current schemas before any operation.
- Ensure RUBE_MANAGE_CONNECTIONS with toolkit 'helpdesk' is ACTIVE before running workflows.
- Use cursor-based pagination with next/prev values; supply both value and ID for forward and backward paging.
- Respect pageSize limits (1-100; default 20) and understand that archived and trash are separate silos.
- Note that views cannot be created or modified via API; canned responses may include placeholders and HTML.
Example Use Cases
- List active tickets in the default 'tickets' silo sorted by createdAt desc with HELPDESK_LIST_TICKETS.
- Open and compare saved agent views from HELPDESK_LIST_VIEWS to pick a filter for a weekly report.
- Fetch all predefined canned responses with HELPDESK_LIST_CANNED_RESPONSES to craft a reply template.
- Inspect custom fields to add an organization-specific data point to a ticket via HELPDESK_LIST_CUSTOM_FIELDS.
- After setup, run a quick verification by listing tickets and confirming the connection status remains ACTIVE.
Frequently Asked Questions
Related Skills
intercom-automation
davepoon/buildwithclaude
Automate Intercom tasks via Rube MCP (Composio): conversations, contacts, companies, segments, admins. Always search tools first for current schemas.
freshdesk-automation
davepoon/buildwithclaude
Automate Freshdesk helpdesk operations including tickets, contacts, companies, notes, and replies via Rube MCP (Composio). Always search tools first for current schemas.
freshservice-automation
davepoon/buildwithclaude
Automate Freshservice ITSM tasks via Rube MCP (Composio): create/update tickets, bulk operations, service requests, and outbound emails. Always search tools first for current schemas.
zendesk-automation
davepoon/buildwithclaude
Automate Zendesk tasks via Rube MCP (Composio): tickets, users, organizations, replies. Always search tools first for current schemas.