Autotask Search
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| AUTOTASK_API_KEY | Yes | Your API key for authentication | |
| AUTOTASK_API_BASE_URL | No | Base URL for the API (default: http://localhost:8000) | http://localhost:8000 |
Instructions
Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.
This server publishes no instructions, or was last inspected before Glama recorded them.
Capabilities
Features and capabilities supported by this server
Protocol revision2025-11-25
| Capability | Details |
|---|---|
| tools | {
"listChanged": true
} |
| logging | {} |
| prompts | {
"listChanged": false
} |
| resources | {
"subscribe": false,
"listChanged": false
} |
| extensions | {
"io.modelcontextprotocol/ui": {}
} |
| experimental | {} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| search_ticketsA | Search Autotask tickets using advanced semantic and keyword search with sentiment filtering and pagination. This tool uses a sophisticated multi-method search combining:
|
| get_ticket_detailsA | Get complete details for a specific ticket including all notes. Use this tool when you need full information about a specific ticket, including the complete description and all human-created notes. This provides more context than search results alone. |
| get_tickets_detailsA | Get complete details for multiple tickets including all notes and time entries. This tool fetches full ticket information for multiple tickets in a single request. More efficient than calling get_ticket_details multiple times when you need details for several tickets. |
| get_related_ticketsA | Find tickets semantically related to a given ticket using vector similarity and AI re-ranking. This tool finds tickets that are similar in content, topic, or issue type by:
This is useful for:
|
| get_tickets_notesA | Get notes for multiple tickets in bulk. Retrieve all human-created notes for specified tickets. You can provide either task IDs, ticket numbers, or both. This is more efficient than calling get_ticket_details multiple times when you only need the notes. |
| search_companiesA | Search for companies (accounts) in Autotask. This tool searches the Autotask companies/accounts database using various matching strategies. It's useful for finding company information, looking up account IDs for filtering other searches, or exploring the customer base. |
| search_contactsA | Search for contacts (account contacts) in Autotask. This tool searches the Autotask contacts database. It's useful for finding contact information, looking up contact IDs for filtering ticket searches, or exploring contacts associated with a specific company. |
| get_tickets_companyA | Get all tickets assigned to one or more companies. This tool retrieves tickets that are formally assigned to the specified companies in the Autotask system. Use this after finding companies with search_companies. Results are returned in reverse chronological order (newest first) without any search ranking or filtering applied. |
| get_tickets_contactA | Get all tickets assigned to one or more contacts. This tool retrieves tickets that are formally assigned to the specified contacts in the Autotask system. Use this after finding contacts with search_contacts. Results are returned in reverse chronological order (newest first) without any search ranking or filtering applied. |
| get_queuesA | Get ticket queues (categories) from Autotask. Queues are used to categorize and route tickets in Autotask. Each ticket is assigned to exactly one queue. This tool retrieves the list of available queues for reference when filtering or categorizing tickets. Note: "Queues" in the Autotask UI are called "TicketCategories" in the API. Both terms refer to the same entity. |
| get_tickets_by_queueA | Get all tickets in a specific queue with optional filtering. This tool retrieves tickets from a specific queue (TicketCategory in Autotask). By default, only open/active tickets are returned (status != Complete). Use include_completed=True to include completed tickets. |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
TDQS
Scored across 11 tools
Some tools have overlapping purposes, particularly get_ticket_details, get_tickets_details, and get_tickets_notes, which all retrieve ticket information and notes. Names like 'get_tickets_details' and 'get_tickets_notes' could easily be confused, though descriptions help clarify the distinctions. The other retrieval tools (by company, contact, queue) are clearly distinct.
Tool names follow a consistent verb_noun pattern with 'search' and 'get' prefixes. Minor inconsistencies exist: get_ticket_details is singular while get_tickets_details is plural, and 'get_tickets_by_queue' uses 'by' while 'get_tickets_company' and 'get_tickets_contact' do not. Overall, the pattern is predictable and readable.
With 11 tools, the server is well-scoped for a search-oriented read-only API. Each tool serves a distinct retrieval purpose, and the count is within the ideal range of 3-15 tools.
The tool set provides a comprehensive read-only surface for ticket searching and retrieval, covering search by text, company, contact, queue, and related tickets, plus batch detail and notes retrieval. Minor gaps exist, such as no direct company/contact detail retrieval beyond search, but the core workflows are covered.