hdls ITSM
hdls ITSM is a headless, MCP-native IT service management backend. It manages incidents, changes, problems, and CIs, operated entirely through named tools your AI assistant calls. It stands in for tools like ServiceNow, Jira Service Management — same job, no UI to run.
💬 Just ask
"Create an incident for Acme, then show me my incidents."
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 ITSM is organized
The headline entity is the incident — start there, then attach the rest to it. Records connect by reference: a change links to a problem. The work_note table is an append-only timeline — every change and note lands there and is never edited or deleted.
| Entity | Purpose | Relates to |
|---|---|---|
incident | An unplanned service disruption, linked to the affected CI and optionally a problem/change. | problem, change |
configuration_item | CMDB entry: a managed service, application, or asset (CI) that incidents/changes reference. | — |
ci_relationship | Directed dependency edge between two configuration items (the CMDB dependency graph). | — |
problem | Root-cause record grouping one or more incidents; tracks known error, workaround, and fix. | — |
change | Change request (standard/normal/emergency) against a CI, moving through the CAB approval lifecycle. | problem |
work_note | Append-only activity log shared by incidents, changes, and problems (polymorphic via entity_type/entity_id). | — |
Common workflows
Each line is one real sequence of tool calls — your assistant chains them for you.
- Set up an incident end to end:
create_incident→link_ci→log_work_note
Tools
Call these at https://hdls.ai/api/mcp/itsm. Required fields you must supply; optional fields refine the call. You never pass tenant_id — it is stamped server-side.
Create
| Tool | What it does | Required | Optional |
|---|---|---|---|
create_incident | Create a new incident. | title | ci_id, problem_id, change_id, description, status, priority |
Update & advance
| Tool | What it does | Required | Optional |
|---|---|---|---|
update_incident | Update an existing incident by id. | id | title, ci_id, problem_id, change_id, description |
link_ci | Link CI to a related record. | id | — |
log_work_note | Log work note. | entity_type, entity_id, body | kind, is_internal, author |
Find & read
| Tool | What it does | Required | Optional |
|---|---|---|---|
search_incidents | Search incidents by free-text and/or column filters (tenant-scoped, paginated). | — | search, filters, limit, orderBy |
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.
incident
| Field | Type | Required | Notes |
|---|---|---|---|
ci_id | id | Links to a configuration_item. | |
problem_id | id | Links to a problem. | |
change_id | id | Links to a change. | |
title | text | Yes | Display name. |
description | text | ||
status | text | Lifecycle state. | |
priority | text | ||
category | text | ||
impact | text | ||
urgency | text | ||
reporter | text | ||
assignee | text | ||
resolved_at | timestamp | ||
data | json | Free-form JSON — custom fields live here. |
configuration_item
| Field | Type | Required | Notes |
|---|---|---|---|
name | text | Yes | Display name. |
ci_type | text | ||
status | text | Lifecycle state. | |
environment | text | ||
owner | text | ||
description | text | ||
data | json | Free-form JSON — custom fields live here. |
ci_relationship
| Field | Type | Required | Notes |
|---|---|---|---|
source_ci_id | id | Yes | Links to a configuration_item. |
target_ci_id | id | Yes | Links to a configuration_item. |
rel_type | text | ||
data | json | Free-form JSON — custom fields live here. |
problem
| Field | Type | Required | Notes |
|---|---|---|---|
ci_id | id | Links to a configuration_item. | |
title | text | Yes | Display name. |
description | text | ||
status | text | Lifecycle state. | |
priority | text | ||
root_cause | text | ||
workaround | text | ||
owner | text | ||
data | json | Free-form JSON — custom fields live here. |
change
| Field | Type | Required | Notes |
|---|---|---|---|
ci_id | id | Links to a configuration_item. | |
problem_id | id | Links to a problem. | |
title | text | Yes | Display name. |
description | text | ||
change_type | text | ||
status | text | Lifecycle state. | |
risk | text | ||
impact | text | ||
assignee | text | ||
planned_start | timestamp | ||
planned_end | timestamp | ||
data | json | Free-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
work_notetimeline is never edited or deleted — it's your audit trail.
Connect
On the concierge (https://hdls.ai/api/mcp), run install_product({ slug: "itsm" }) (admin/owner) to enable it for your workspace, then add https://hdls.ai/api/mcp/itsm 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_incident
Arguments: {
"title": "Acme Corp"
}