hdls Support

hdls Support is a full helpdesk your assistant runs end to end — tickets, the back-and-forth conversation on each one, a searchable knowledge base, and the requesters (your customers) who raise them. No agent console to log into: your assistant creates tickets, drafts replies, and closes them out.

The headline entity is the ticket. Requesters are first-class external parties, so a ticket always knows who it's for. suggest_reply and search_kb lean on the knowledge base to answer faster, and semantic_search_tickets finds similar past issues by meaning, not just keywords.

Common workflows

  • Handle an incoming issue: create_ticketsearch_kb / suggest_replyadd_messageset_status.
  • Deflect with knowledge: search_kb before replying; reuse the best article.
  • Find precedent: semantic_search_tickets to surface how similar tickets were resolved.

hdls Support is a headless, MCP-native helpdesk & ticketing backend. It manages tickets, conversations, and a knowledge base, operated entirely through named tools your AI assistant calls. It stands in for tools like Zendesk, Intercom — same job, no UI to run.

💬 Just ask

"Open a ticket for Jane about a failed login, then show me all open tickets."

You don't call these tools yourself — just tell your assistant in plain English. Everything below is the reference for when you (or your assistant) want the exact details.

How Support is organized

The headline entity is the ticket — start there, then attach the rest to it. Records connect by reference: a requester links to an org. The message table is an append-only timeline — every change and note lands there and is never edited or deleted.

EntityPurposeRelates to
ticketA support request tracked from open through resolution.requester, org, sla_policy
orgCustomer organization (account) that requesters belong to.
requesterEnd user (customer contact) who submits and follows support tickets.org
sla_policyService-level targets (first response / resolution) applied to tickets by priority.
kb_articleKnowledge-base article surfaced to agents/requesters; semantically searchable for suggested replies.
macroReusable canned reply plus optional field actions applied to a ticket in one step.
messageAppend-only conversation timeline for a ticket (public replies and internal notes).ticket

Tools

Call these at https://hdls.ai/api/mcp/support. Required fields you must supply; optional fields refine the call. You never pass tenant_id — it is stamped server-side.

Create

ToolWhat it doesRequiredOptional
create_ticketCreate a new ticket.subjectrequester_id, org_id, sla_policy_id, body, status, priority

Update & advance

ToolWhat it doesRequiredOptional
set_statusSet the status.idstatus
suggest_replyDraft a suggested reply.id

Find & read

ToolWhat it doesRequiredOptional
search_kbSearch KB by free-text and/or column filters (tenant-scoped, paginated).search, filters, limit, orderBy
semantic_search_ticketsFind search tickets by meaning, not just keywords.search, filters, limit, orderBy

Timeline

ToolWhat it doesRequiredOptional
add_messageAdd a message.ticket_id, bodyauthor_type, author, is_public

Field lists come from the product's live schema and are embedded in each tool's own description — read the tool description for the exact, current fields.

Field reference

Every field you can set on each record. Custom fields you add live alongside these in data.

ticket

FieldTypeRequiredNotes
requester_ididLinks to a requester.
org_ididLinks to an org.
sla_policy_ididLinks to a sla_policy.
subjecttextYes
bodytext
statustextLifecycle state.
prioritytext
channeltext
assigneetext
tagslistFree-form labels.
due_attimestamp
solved_attimestamp
datajsonFree-form JSON — custom fields live here.

org

FieldTypeRequiredNotes
nametextYesDisplay name.
domaintext
notestext
datajsonFree-form JSON — custom fields live here.

requester

FieldTypeRequiredNotes
org_ididLinks to an org.
nametextYesDisplay name.
emailtext
phonetext
datajsonFree-form JSON — custom fields live here.

sla_policy

FieldTypeRequiredNotes
nametextYesDisplay name.
prioritytext
first_response_minsnumber
resolution_minsnumber
is_activetrue / false
datajsonFree-form JSON — custom fields live here.

kb_article

FieldTypeRequiredNotes
titletextYesDisplay name.
bodytext
statustextLifecycle state.
tagslistFree-form labels.
authortext
datajsonFree-form JSON — custom fields live here.

macro

FieldTypeRequiredNotes
nametextYesDisplay name.
bodytext
actionsjson
is_activetrue / false
datajsonFree-form JSON — custom fields live here.

Tailor it with custom fields

Add fields without a schema change. add_custom_field defines one, list_custom_fields shows what's defined, and promote_custom_field (admin) shares a personal field with the whole workspace. The value lives in each row's data (JSON) and is set and read through the normal record tools. See Products, tools & custom fields for the full model.

Roles & safety

  • Tenant isolation is automatic. Your credential is pinned to one workspace; you never pass tenant_id, and you can only ever see your own data (enforced by Postgres row-level security).
  • Role-gated. Permissions run reader < member < admin < owner. Installing a product and promoting a custom field workspace-wide need admin/owner.
  • History is append-only. The message timeline is never edited or deleted — it's your audit trail.

Connect

On the concierge (https://hdls.ai/api/mcp), run install_product({ slug: "support" }) (admin/owner) to enable it for your workspace, then add https://hdls.ai/api/mcp/support as a connector in your assistant — see Connect your assistant.

A worked example

The literal call your assistant makes when you ask it to create the headline record:

Tool: create_ticket
Arguments: {
  "subject": "example"
}

See All products · Connect your assistant · Automation