hdls People
hdls People is a headless, MCP-native HR & people management backend. It manages employees, time off, and org structure, operated entirely through named tools your AI assistant calls. It stands in for tools like BambooHR, Workday — same job, no UI to run.
💬 Just ask
"Add Sam as a new employee starting Monday, then show me everyone in Engineering."
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 People is organized
The headline entity is the employee — start there, then attach the rest to it. Records connect by reference: a compensation links to an employee; a time_off_request links to an employee. The employment_event table is an append-only timeline — every change and note lands there and is never edited or deleted.
| Entity | Purpose | Relates to |
|---|---|---|
employee | A person employed by the tenant, with org placement and lifecycle. | department |
department | Organizational unit; self-references parent_id to form the org tree. | — |
compensation | Effective-dated pay records for an employee; latest effective_date is current comp. | employee |
time_off_policy | Leave type with accrual rules (vacation, sick, etc.) referenced by time-off requests. | — |
time_off_request | An employee request for leave against a policy, with approval workflow. | employee |
employment_event | Append-only HR timeline: every material change in an employee lifecycle. | employee |
Common workflows
Each line is one real sequence of tool calls — your assistant chains them for you.
- Set up an employee end to end:
create_employee→request_time_off
Tools
Call these at https://hdls.ai/api/mcp/hr. 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_employee | Create a new employee. | first_name, last_name | department_id, manager_id, email, phone, job_title, employment_type |
Update & advance
| Tool | What it does | Required | Optional |
|---|---|---|---|
update_employee | Update an existing employee by id. | id | first_name, last_name, department_id, manager_id, email |
request_time_off | Log a time-off request. | employee_id, start_date, end_date | policy_id, hours, status, reason, approver_id, decided_at |
Find & read
| Tool | What it does | Required | Optional |
|---|---|---|---|
search_people | Search people by free-text and/or column filters (tenant-scoped, paginated). | — | search, filters, limit, orderBy |
list_org | Search org 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.
employee
| Field | Type | Required | Notes |
|---|---|---|---|
department_id | id | Links to a department. | |
manager_id | id | Reference to a related record. | |
first_name | text | Yes | |
last_name | text | Yes | |
email | text | ||
phone | text | ||
job_title | text | ||
employment_type | text | ||
status | text | Lifecycle state. | |
hire_date | date | ||
termination_date | date | ||
location | text | ||
bio | text | ||
data | json | Free-form JSON — custom fields live here. |
department
| Field | Type | Required | Notes |
|---|---|---|---|
parent_id | id | Reference to a related record. | |
name | text | Yes | Display name. |
code | text | ||
data | json | Free-form JSON — custom fields live here. |
compensation
| Field | Type | Required | Notes |
|---|---|---|---|
employee_id | id | Yes | Links to an employee. |
amount | numeric(14,2) | Yes | |
currency | text | ||
pay_period | text | ||
effective_date | date | Yes | |
reason | text | ||
data | json | Free-form JSON — custom fields live here. |
time_off_policy
| Field | Type | Required | Notes |
|---|---|---|---|
name | text | Yes | Display name. |
kind | text | ||
accrual_days_per_year | numeric(6,2) | ||
is_paid | true / false | ||
is_active | true / false | ||
data | json | Free-form JSON — custom fields live here. |
time_off_request
| Field | Type | Required | Notes |
|---|---|---|---|
employee_id | id | Yes | Links to an employee. |
policy_id | id | Reference to a related record. | |
start_date | date | Yes | |
end_date | date | Yes | |
hours | numeric(7,2) | ||
status | text | Lifecycle state. | |
reason | text | ||
approver_id | id | Reference to a related record. | |
decided_at | 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
employment_eventtimeline is never edited or deleted — it's your audit trail.
Connect
On the concierge (https://hdls.ai/api/mcp), run install_product({ slug: "hr" }) (admin/owner) to enable it for your workspace, then add https://hdls.ai/api/mcp/hr 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_employee
Arguments: {
"first_name": "Ada",
"last_name": "Lovelace"
}