hdls Field

hdls Field is a headless, MCP-native field service management backend. It manages jobs, technicians, and site visits, operated entirely through named tools your AI assistant calls. It stands in for tools like ServiceTitan, Jobber — same job, no UI to run.

💬 Just ask

"Create a job for Acme, then show me my jobs."

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 Field is organized

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

EntityPurposeRelates to
jobA customer service request scheduled and fulfilled via one or more site visits.
technicianA field worker who is dispatched to visits; carries skills for job matching.
visitA scheduled on-site appointment for a job, assigned to a technician with arrival/completion times.job, technician
job_activityAppend-only timeline shared by jobs and visits (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 a job end to end: create_jobassign_technicianlog_visit
  • Move a job through its lifecycle: create_jobupdate_status

Tools

Call these at https://hdls.ai/api/mcp/fieldservice. 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_jobCreate a new job.titlejob_number, description, customer_name, service_address, job_type, status

Update & advance

ToolWhat it doesRequiredOptional
assign_technicianAssign technician to a person or record.nameemail, phone, skills, status, data
update_statusUpdate the status of a job by id.idstatus
log_visitLog visit.job_idtechnician_id, status, scheduled_start, scheduled_end, arrived_at, completed_at

Find & read

ToolWhat it doesRequiredOptional
search_jobsSearch jobs 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.

job

FieldTypeRequiredNotes
job_numbertext
titletextYesDisplay name.
descriptiontext
customer_nametext
service_addresstext
job_typetext
statustextLifecycle state.
prioritytext
quoted_amountnumeric(14,2)
currencytext
scheduled_fortimestamp
completed_attimestamp
datajsonFree-form JSON — custom fields live here.

technician

FieldTypeRequiredNotes
nametextYesDisplay name.
emailtext
phonetext
skillslist
statustextLifecycle state.
datajsonFree-form JSON — custom fields live here.

visit

FieldTypeRequiredNotes
job_ididYesLinks to a job.
technician_ididLinks to a technician.
statustextLifecycle state.
scheduled_starttimestamp
scheduled_endtimestamp
arrived_attimestamp
completed_attimestamp
summarytext
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 job_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: "fieldservice" }) (admin/owner) to enable it for your workspace, then add https://hdls.ai/api/mcp/fieldservice 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_job
Arguments: {
  "title": "Acme Corp"
}

See All products · Connect your assistant · Automation