Judge.me
Collect, moderate and reply to Judge.me product reviews, and manage reviewers, shop settings and webhooks.
About
Judge.me ships in the w6w first-party pack. It declares 16 actions, 2 health checks, and the host runs its code in a sandbox that never sees the credential.
- App id
io.w6w.judgeme- Version
- 0.1.0
- Author
- w6w
- Licence
- MIT
- Categories
- Commerce & Payments · Marketing
Overview
Judge.me is an ecommerce product-reviews platform used mainly by Shopify, WooCommerce and BigCommerce stores. This app covers the review lifecycle a workflow needs: list, fetch, count and create reviews, and publish or hide (curate) them once they’re in. It also manages the reviewer record behind each review — looked up by Judge.me’s internal id, the store platform’s external id, or email — and can submit the data requests Judge.me’s own GDPR/CCPA tooling expects.
Beyond reviews themselves, it covers the surfaces a store operator manages alongside them: public and private replies (the latter emails the reviewer without publishing anything), the shop’s own Judge.me-held profile and settings, and webhooks for reacting to review events instead of polling.
Judge.me’s storefront widgets (the HTML fragments a theme embeds directly on product pages) are a display concern, not a workflow operation, and are deliberately out of scope here — as is the separate paid Checkout Comments add-on. Judge.me’s own OpenAPI document also documents a second, OAuth2-based credential, but never publishes the token endpoint it would need — this app authenticates with an API key instead, which is the credential Judge.me’s own document fully specifies.
Build with Judge.me
Three routes to the same 16 actions. The Workflow tab is generated from Judge.me's own manifest and carries its real ids, so it is copy-pasteable; the Code and CLI examples are the same call for any action on any app, so every app-specific value in them is a blank you fill in.
Count Reviews
count-reviews Count reviews for a product or reviewer, or for the whole shop when both are omitted. The vendor's OpenAPI document does not specify a response schema for this endpoint, so the raw response body is returned as-is.
Create Private Reply
create-private-reply Email a reviewer privately about their review, without publishing a public reply.
Create Reply
create-reply Post a public reply to a review, shown on the Judge.me review widget. Defaults to also emailing the reviewer, per Judge.me's own default.
Create Review
create-review Submit a web review, the same way a storefront's own review form does. Needs no Connection at all — Judge.me documents this endpoint as unauthenticated. Creates nothing if the store has disabled web reviews, with no distinct signal for that case.
Delete Webhook
delete-webhook Unsubscribe a URL from a Judge.me event, identified by the exact key/url pair.
Get Reviewer
get-reviewer Fetch a reviewer's name, email and phone by Judge.me id, external id or email.
Get Shop Info
get-shop-info Read the connected store's Judge.me plan, owner, email, platform and related metadata. The vendor's OpenAPI document does not give this endpoint a real response schema — see the source comment for what that means here.
List Reviews
list-reviews List reviews for the shop, or for one product when Product ID is given. Product ID and Reviewer ID are Judge.me's internal ids, not the store platform's external ids.
List Settings
list-settings Read store settings values, optionally narrowed to specific keys. The vendor documents a handful of example keys but not the full set.
Request Reviewer Data
request-reviewer-data Submit a data request for a reviewer, identified by email and a list of the store platform's own order ids. Response shape is undocumented by Judge.me.
Publish or Hide Review
update-review Publish (curated=ok) or hide (curated=spam) a review. Judge.me does not support editing review content via the API.
Create or Update Reviewer
update-reviewer Create a reviewer if none matches, or update the one found by id/external id/email.
Update Shop
update-shop Update the connected store's Judge.me-held information (domain, owner, contact info, country, timezone, plan). Only the fields provided are sent.
A workflow step names the app and the action, and the editor fills in the
connection when you pick one. This is the Step shape from the
workflow spec, carrying Judge.me's real ids.
{
"manifestVersion": "2",
"name": "judgeme-example",
"steps": [
{
"id": "create-private-reply",
"uses": {
"app": "io.w6w.judgeme",
"action": "create-private-reply",
"connection": "conn_YOUR_CONNECTION_ID"
},
"with": {
"reviewId": "<reviewId>",
"emailSubject": "<emailSubject>",
"emailBody": "<emailBody>"
}
}
]
}Here are some of the things you can do
-
Create Private Reply
performcreate-private-reply -
Count Reviews
readcount-reviews -
Create Reply
performcreate-reply -
Create Review
performcreate-review -
Create Webhook
performcreate-webhook
+11 more actions available
Every app-specific value here is a blank you have to fill in. An
app action is reached through the connection that authenticates it, so the
address is a connection id, not the app id — and connections belong to your account,
so a public page cannot know yours. Create one for Judge.me, then fill in
the three blanks: conn_YOUR_CONNECTION_ID, the action key, and the
parameters that action declares. The call itself is real — the shape is transcribed
from the studio's own snippet builder, which prints the same kind of blanks — but
nothing in it is specific to Judge.me. The Workflow tab is where this app's
real ids are.
npm install @w6w/sdkyarn add @w6w/sdkpnpm add @w6w/sdkdeno add npm:@w6w/sdkimport { W6wClient, isActionRun } from "@w6w/sdk";
// Reads W6W_BASE_URL and W6W_TOKEN from the environment when omitted.
const client = new W6wClient();
const envelope = await client.run({
urn: "conn_YOUR_CONNECTION_ID",
action: "create-private-reply",
payload: {
reviewId: "<value>",
emailSubject: "<value>",
emailBody: "<value>",
// sendPrivateEmail: "<value>",
},
});
if (isActionRun(envelope)) console.log(envelope.value);npm install -g @w6w/cliw6w run conn_YOUR_CONNECTION_ID --action create-private-reply --payload '{"reviewId":"<value>","emailSubject":"<value>","emailBody":"<value>"}'Give an AI agent Judge.me — without giving it Judge.me's credentials. One MCP endpoint exposes every app, function and workflow the caller is entitled to, as tools it can discover and run. Access is granted per team while we onboard.
One tool call{
"name": "w6w_invoke",
"arguments": {
"ref": "app:io.w6w.judgeme#create-private-reply",
"input": {
"reviewId": "<reviewId>",
"emailSubject": "<emailSubject>",
"emailBody": "<emailBody>"
}
}
}
Every tool names its target with a single ref. The
app: form above doesn't name a connection at all — the
host resolves which of the caller's Judge.me connections to sign
with, and refuses rather than guesses when the answer is ambiguous.
What the agent gets
Credentials it can't read
The token is attached host-side, at the moment of the call. It is never a tool argument, never in the model's context, and never in a transcript — so a prompt injection has nothing to exfiltrate.
A tool surface scoped to the caller
Tools are derived per end user from what that person has actually connected and is entitled to — not one shared bot identity carrying the union of everyone's access.
A durable workflow in one call
Multi-step work runs on the workflow engine and returns a run handle the agent can poll — retries, branching and state survive the conversation that started them.
Health-aware discovery
Judge.me's declared health checks are on the surface too, so an agent can tell "the vendor is down" from "your credential expired" before it burns a retry on either.
The MCP surface is part of the hosted platform. Judge.me itself is MIT, and the runtime that executes it is source-available (FSL).
Health checks
Judge.me declares its own checks, so its health is a property of the app rather than something the host guesses at.
Judge.me platform status
Component status from status.judge.me, scoped to the Admin/API and Storefront widgets components this app's actions depend on.