hdls Hire

hdls Hire is a headless, MCP-native applicant tracking & recruiting backend. It manages candidates, jobs, and interview feedback, operated entirely through named tools your AI assistant calls. It stands in for tools like Greenhouse, Lever — same job, no UI to run.

💬 Just ask

"Add a candidate for the Sales role and move them to the interview stage."

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 Hire is organized

The headline entity is the candidate — start there, then attach the rest to it. Records connect by reference: a stage links to a job; an application links to a candidate and a job and a stage; a scorecard links to an application. The candidate_activity table is an append-only timeline — every change and note lands there and is never edited or deleted.

Entity	Purpose	Relates to
`candidate`	A person in the talent pool; may apply to multiple jobs.	—
`job`	An open requisition candidates apply to; owns its pipeline stages.	—
`stage`	Ordered pipeline step belonging to a job (applied -> screen -> ... -> hired/rejected).	`job`
`application`	A candidate moving through one job pipeline; links candidate, job, and current stage.	`candidate`, `job`, `stage`
`scorecard`	Structured interview feedback for an application (recommendation + rating + notes).	`application`
`candidate_activity`	Append-only recruiting timeline: notes, emails, stage moves, feedback for a candidate.	`candidate`, `application`

Common workflows

Each line is one real sequence of tool calls — your assistant chains them for you.

Set up a candidate end to end: create_candidate → log_feedback → open_job
Move a candidate through its lifecycle: create_candidate → move_stage

Tools

Call these at https://hdls.ai/api/mcp/ats. 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_candidate`	Create a new candidate.	`first_name`, `last_name`	`email`, `phone`, `headline`, `resume_text`, `source`, `tags`

Update & advance

Tool	What it does	Required	Optional
`move_stage`	Move a stage.	`id`, `stage`	—
`log_feedback`	Log feedback.	`id`	—
`open_job`	Open a new job.	`title`	`department`, `location`, `employment_type`, `status`, `description`, `hiring_manager`

Find & read

Tool	What it does	Required	Optional
`search_candidates`	Search candidates 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.

`candidate`

Field	Type	Required	Notes
`first_name`	text	Yes
`last_name`	text	Yes
`email`	text
`phone`	text
`headline`	text
`resume_text`	text
`source`	text
`tags`	list		Free-form labels.
`data`	json		Free-form JSON — custom fields live here.

`job`

Field	Type	Required	Notes
`title`	text	Yes	Display name.
`department`	text
`location`	text
`employment_type`	text
`status`	text		Lifecycle state.
`description`	text
`hiring_manager`	text
`openings`	number
`data`	json		Free-form JSON — custom fields live here.

`stage`

Field	Type	Required	Notes
`job_id`	id	Yes	Links to a `job`.
`name`	text	Yes	Display name.
`kind`	text
`position`	number
`data`	json		Free-form JSON — custom fields live here.

`application`

Field	Type	Required	Notes
`candidate_id`	id	Yes	Links to a `candidate`.
`job_id`	id	Yes	Links to a `job`.
`stage_id`	id		Links to a `stage`.
`status`	text		Lifecycle state.
`rating`	number
`rejected_reason`	text
`applied_at`	timestamp
`data`	json		Free-form JSON — custom fields live here.

`scorecard`

Field	Type	Required	Notes
`application_id`	id	Yes	Links to an `application`.
`interviewer`	text
`recommendation`	text
`overall_rating`	number
`notes`	text
`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 candidate_activity timeline is never edited or deleted — it's your audit trail.

Connect

On the concierge (https://hdls.ai/api/mcp), run install_product({ slug: "ats" }) (admin/owner) to enable it for your workspace, then add https://hdls.ai/api/mcp/ats 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_candidate
Arguments: {
  "first_name": "Ada",
  "last_name": "Lovelace"
}

See All products · Connect your assistant · Automation