hdls Workflows

hdls Workflows is a headless, MCP-native automation (if-this-then-that) backend. It manages workflows, if-this-then-that rules, actions, dependencies, and run history, operated entirely through named tools your AI assistant calls. It stands in for tools like Zapier, Make, n8n — same job, no UI to run.

💬 Just ask

"When a deal is won, create an onboarding task — set that rule up for me." · "Show me what's run recently."

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 Workflows is organized

The headline entity is the rule — start there, then attach the rest to it. Records connect by reference: an action links to a rule; a dependency links to a workflow and a rule; a run_step links to a run and an action. The run table is an append-only timeline — every change and note lands there and is never edited or deleted.

EntityPurposeRelates to
ruleAn if-this-then-that rule: trigger + condition tree; actions live in workflows.action.workflow
workflowWorkflow records.
actionAn ordered step in a rule's then/else branch (a tool call, message, ticket, etc).rule
dependencyA dependency linked to a workflow and a rule.workflow, rule
run_stepA run step linked to a run and an action.run, action
runAppend-only: each rule firing. The history the AI mines to learn if->then patterns.workflow, rule

Common workflows

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

  • Set up a rule end to end: create_workflowadd_ruleadd_action
  • Move a rule through its lifecycle: create_workflowactivate_workflow

Tools

Call these at https://hdls.ai/api/mcp/workflows. 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_workflowCreate a new workflow.namedescription, status, data

Update & advance

ToolWhat it doesRequiredOptional
add_ruleAdd a rule.workflow_id, nametrigger_type, trigger_match, condition, position, active, data
add_actionAdd an action.rule_id, kindbranch, config, position
link_dependencyLink dependency to a related record.workflow_id, rule_id, depends_on_rule_id
activate_workflowActivate a workflow.id

Find & read

ToolWhat it doesRequiredOptional
list_runsSearch runs 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.

rule

FieldTypeRequiredNotes
workflow_ididYesLinks to a workflow.
nametextYesDisplay name.
trigger_typetext
trigger_matchjson
conditionjson
positionnumber
activetrue / false
datajsonFree-form JSON — custom fields live here.

workflow

FieldTypeRequiredNotes
nametextYesDisplay name.
descriptiontext
statustextLifecycle state.
datajsonFree-form JSON — custom fields live here.

action

FieldTypeRequiredNotes
rule_ididYesLinks to a rule.
branchtext
kindtextYes
configjson
positionnumber

dependency

FieldTypeRequiredNotes
workflow_ididYesLinks to a workflow.
rule_ididYesLinks to a rule.
depends_on_rule_ididYesReference to a related record.

run_step

FieldTypeRequiredNotes
run_ididYesLinks to a run.
action_ididLinks to an action.
statustextLifecycle state.
outputjson

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 run timeline is never edited or deleted — it's your audit trail.

Connect

On the concierge (https://hdls.ai/api/mcp), run install_product({ slug: "workflows" }) (admin/owner) to enable it for your workspace, then add https://hdls.ai/api/mcp/workflows 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_workflow
Arguments: {
  "name": "Acme Corp"
}

See All products · Connect your assistant · Automation