hdls Reviews
hdls Reviews is a headless, MCP-native reviews & testimonials backend. It manages reviews, ratings, and responses, operated entirely through named tools your AI assistant calls. It stands in for tools like Trustpilot, Yotpo — same job, no UI to run.
💬 Just ask
"Show me my latest reviews and draft a reply to the newest one-star."
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 Reviews is organized
The headline entity is the review — start there, then attach the rest to it. Records connect by reference: a response links to a review. The moderation_event table is an append-only timeline — every change and note lands there and is never edited or deleted.
| Entity | Purpose | Relates to |
|---|---|---|
review | A star rating plus written review of a subject, with moderation state and semantic search. | subject |
subject | The entity being reviewed (product, company, location…); holds the denormalised rating aggregate. | — |
response | A reply to a review (typically the official business response). | review |
moderation_event | Append-only audit trail of every moderation action and status transition on a review. | review |
Tools
Call these at https://hdls.ai/api/mcp/reviews. 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_review | Create a new review. | subject_id, rating, body | title, author_name, author_email, status, verified, sentiment |
Update & advance
| Tool | What it does | Required | Optional |
|---|---|---|---|
moderate_review | Moderate a review. | id | — |
respond_to_review | Respond the review to review. | id | — |
Find & read
| Tool | What it does | Required | Optional |
|---|---|---|---|
search_reviews | Search reviews by free-text and/or column filters (tenant-scoped, paginated). | — | search, filters, limit, orderBy |
aggregate_rating | Aggregate ratings into a summary score. | — | — |
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.
review
| Field | Type | Required | Notes |
|---|---|---|---|
subject_id | id | Yes | Links to a subject. |
rating | number | Yes | |
title | text | Display name. | |
body | text | Yes | |
author_name | text | ||
author_email | text | ||
status | text | Lifecycle state. | |
verified | true / false | ||
sentiment | text | ||
helpful_count | number | ||
data | json | Free-form JSON — custom fields live here. |
subject
| Field | Type | Required | Notes |
|---|---|---|---|
kind | text | ||
external_ref | text | ||
name | text | Yes | Display name. |
rating_avg | numeric(3,2) | ||
rating_count | number | ||
data | json | Free-form JSON — custom fields live here. |
response
| Field | Type | Required | Notes |
|---|---|---|---|
review_id | id | Yes | Links to a review. |
body | text | Yes | |
author | text | ||
is_official | true / false | ||
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
moderation_eventtimeline is never edited or deleted — it's your audit trail.
Connect
On the concierge (https://hdls.ai/api/mcp), run install_product({ slug: "reviews" }) (admin/owner) to enable it for your workspace, then add https://hdls.ai/api/mcp/reviews 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_review
Arguments: {
"subject_id": "<subject-id>",
"rating": 5,
"body": "Notes go here."
}