Freshservice Automation logo

Freshservice Automation

CommunityPopular
davepoon
freshservice-automation

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.

Overview

Publisherdavepoon
Repositorybuildwithclaude
Skill namefreshservice-automation
Stars
3.6K
Forks
586
Bundled files
Instructions only
LicenseMIT
Links
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • Self-contained

    Everything the model needs lives in the instructions — no extra files to sync.

  • Open source

    Published by davepoon on GitHub. Read the source before you install it.

Installation

Install the Freshservice Automation AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
    https://github.com/davepoon/buildwithclaude/tree/main/plugins/all-skills/skills/freshservice-automation
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/davepoon/buildwithclaude.git /tmp/buildwithclaude
mkdir -p .claude/skills
cp -r /tmp/buildwithclaude/plugins/all-skills/skills/freshservice-automation .claude/skills/freshservice-automation
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Freshservice Automation in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Freshservice Automation on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Freshservice Automation is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

Freshservice Automation via Rube MCP

Automate Freshservice IT Service Management operations through Composio's Freshservice toolkit via Rube MCP.

Toolkit docs: composio.dev/toolkits/freshservice

Prerequisites

  • Rube MCP must be connected (RUBE_SEARCH_TOOLS available)
  • Active Freshservice connection via RUBE_MANAGE_CONNECTIONS with toolkit freshservice
  • 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.

  1. Verify Rube MCP is available by confirming RUBE_SEARCH_TOOLS responds
  2. Call RUBE_MANAGE_CONNECTIONS with toolkit freshservice
  3. If connection is not ACTIVE, follow the returned auth link to complete Freshservice authentication
  4. Confirm connection status shows ACTIVE before running any workflows

Core Workflows

1. List and Search Tickets

When to use: User wants to find, list, or search for tickets

Tool sequence:

  1. FRESHSERVICE_LIST_TICKETS - List tickets with optional filtering and pagination [Required]
  2. FRESHSERVICE_GET_TICKET - Get detailed information for a specific ticket [Optional]

Key parameters for listing:

  • filter: Predefined filter ('all_tickets', 'deleted', 'spam', 'watching')
  • updated_since: ISO 8601 timestamp to get tickets updated after this time
  • order_by: Sort field ('created_at', 'updated_at', 'status', 'priority')
  • order_type: Sort direction ('asc' or 'desc')
  • page: Page number (1-indexed)
  • per_page: Results per page (1-100, default 30)
  • include: Additional fields ('requester', 'stats', 'description', 'conversations', 'assets')

Key parameters for get:

  • ticket_id: Unique ticket ID or display_id
  • include: Additional fields to include

Pitfalls:

  • By default, only tickets created within the past 30 days are returned
  • Use updated_since to retrieve older tickets
  • Each include value consumes additional API credits
  • page is 1-indexed; minimum value is 1
  • per_page max is 100; default is 30
  • Ticket IDs can be the internal ID or the display_id shown in the UI

2. Create a Ticket

When to use: User wants to log a new incident or request

Tool sequence:

  1. FRESHSERVICE_CREATE_TICKET - Create a new ticket [Required]

Key parameters:

  • subject: Ticket subject line (required)
  • description: HTML description of the ticket (required)
  • status: Ticket status - 2 (Open), 3 (Pending), 4 (Resolved), 5 (Closed) (required)
  • priority: Ticket priority - 1 (Low), 2 (Medium), 3 (High), 4 (Urgent) (required)
  • email: Requester's email address (provide either email or requester_id)
  • requester_id: User ID of the requester
  • type: Ticket type ('Incident' or 'Service Request')
  • source: Channel - 1 (Email), 2 (Portal), 3 (Phone), 4 (Chat), 5 (Twitter), 6 (Facebook)
  • impact: Impact level - 1 (Low), 2 (Medium), 3 (High)
  • urgency: Urgency level - 1 (Low), 2 (Medium), 3 (High), 4 (Critical)

Pitfalls:

  • subject, description, status, and priority are all required
  • Either email or requester_id must be provided to identify the requester
  • Status and priority use numeric codes, not string names
  • Description supports HTML formatting
  • If email does not match an existing contact, a new contact is created

3. Bulk Update Tickets

When to use: User wants to update multiple tickets at once

Tool sequence:

  1. FRESHSERVICE_LIST_TICKETS - Find tickets to update [Prerequisite]
  2. FRESHSERVICE_BULK_UPDATE_TICKETS - Update multiple tickets [Required]

Key parameters:

  • ids: Array of ticket IDs to update (required)
  • update_fields: Dictionary of fields to update (required)
    • Allowed keys: 'subject', 'description', 'status', 'priority', 'responder_id', 'group_id', 'type', 'tags', 'custom_fields'

Pitfalls:

  • Bulk update performs sequential updates internally; large batches may take time
  • All specified tickets receive the same field updates
  • If one ticket update fails, others may still succeed; check response for individual results
  • Cannot selectively update different fields per ticket in a single call
  • Custom fields must use their internal field names, not display names

4. Create Ticket via Outbound Email

When to use: User wants to create a ticket by sending an outbound email notification

Tool sequence:

  1. FRESHSERVICE_CREATE_TICKET_OUTBOUND_EMAIL - Create ticket with email notification [Required]

Key parameters:

  • email: Requester's email address (required)
  • subject: Email subject / ticket subject (required)
  • description: HTML email body content
  • status: Ticket status (2=Open, 3=Pending, 4=Resolved, 5=Closed)
  • priority: Ticket priority (1=Low, 2=Medium, 3=High, 4=Urgent)
  • cc_emails: Array of CC email addresses
  • email_config_id: Email configuration ID for the sender address
  • name: Requester name

Pitfalls:

  • This creates a standard ticket via the /api/v2/tickets endpoint while sending an email
  • If the email does not match an existing contact, a new contact is created with the provided name
  • email_config_id determines which email address the notification appears to come from

5. Create Service Requests

When to use: User wants to submit a service catalog request

Tool sequence:

  1. FRESHSERVICE_CREATE_SERVICE_REQUEST - Create a service request for a catalog item [Required]

Key parameters:

  • item_display_id: Display ID of the catalog item (required)
  • email: Requester's email address
  • quantity: Number of items to request (default: 1)
  • custom_fields: Custom field values for the service item form
  • parent_ticket_id: Display ID of a parent ticket (for child requests)

Pitfalls:

  • item_display_id can be found in Admin > Service Catalog > item URL (e.g., /service_catalog/items/1)
  • Custom fields keys must match the service item form field names
  • Quantity defaults to 1 if not specified
  • Service requests follow the approval workflow defined for the catalog item

Common Patterns

Status Code Reference

CodeStatus
2Open
3Pending
4Resolved
5Closed

Priority Code Reference

CodePriority
1Low
2Medium
3High
4Urgent

Pagination

  • Use page (1-indexed) and per_page (max 100) parameters
  • Increment page by 1 each request
  • Continue until returned results count < per_page
  • Default page size is 30

Finding Tickets by Date Range

1. Call FRESHSERVICE_LIST_TICKETS with updated_since='2024-01-01T00:00:00Z'
2. Optionally add order_by='updated_at' and order_type='desc'
3. Paginate through results

Known Pitfalls

Numeric Codes:

  • Status and priority use numeric values, not strings
  • Source channel uses numeric codes (1-6)
  • Impact and urgency use numeric codes (1-3 or 1-4)

Date Filtering:

  • Default returns only tickets from the last 30 days
  • Use updated_since parameter for older tickets
  • Date format is ISO 8601 (e.g., '2024-01-01T00:00:00Z')

Rate Limits:

  • Freshservice API has per-account rate limits
  • Each include option consumes additional API credits
  • Implement backoff on 429 responses

Response Parsing:

  • Response data may be nested under data or data.data
  • Parse defensively with fallback patterns
  • Ticket IDs are numeric integers

Quick Reference

TaskTool SlugKey Params
List ticketsFRESHSERVICE_LIST_TICKETSfilter, updated_since, page, per_page
Get ticketFRESHSERVICE_GET_TICKETticket_id, include
Create ticketFRESHSERVICE_CREATE_TICKETsubject, description, status, priority, email
Bulk updateFRESHSERVICE_BULK_UPDATE_TICKETSids, update_fields
Outbound email ticketFRESHSERVICE_CREATE_TICKET_OUTBOUND_EMAILemail, subject, description
Service requestFRESHSERVICE_CREATE_SERVICE_REQUESTitem_display_id, email, quantity

Powered by Composio

Frequently asked questions

What does the Freshservice Automation AI skill do?

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.

Why use Freshservice Automation on TypingMind?

Because you install it once and use it with any model. Freshservice Automation is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Freshservice Automation in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/davepoon/buildwithclaude/tree/main/plugins/all-skills/skills/freshservice-automation. TypingMind reads its SKILL.md and installs it as a skill you can enable per chat.

Which AI models can use Freshservice Automation?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Freshservice Automation?

As many as you like. As long as a model supports skills, you can use Freshservice Automation with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Freshservice Automation AI skill free?

Yes. It is published on GitHub by davepoon under the MIT license. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇