# Judge.me MCP connector The Judge.me connector brings product reviews, reviewers, review widgets and webhooks to Claude, ChatGPT, Cursor and the Elaichi Agent, so each person can find, summarize and update reviews inside their own Judge.me access with every action logged. Source: https://elaichi.ai/connectors/judge/ ## Facts | | | | --- | --- | | Application | Judge.me | | Category | Ecommerce | | AI tools | 34 | | Authentication | Connects with an API key | | Needs your own OAuth app | Yes | | MCP endpoint | https://api.elaichi.ai/mcp | | Works with | Claude, ChatGPT, Cursor, any MCP client, and the Elaichi Agent | | Tools advertised by name | No. 34 tools is past the 30-tool threshold, so clients use `search_tools` and `execute_tool` | ## What you can ask once Judge.me is connected - Show me one star Judge.me reviews from this week - Summarize what reviewers say about the linen shirt - List the review widgets live on the store ## Connect Judge.me in Elaichi This happens once for the organization, before any client is involved. 1. Open Connections, choose Add connection, and pick Judge.me. 2. Optionally set Share with, then press Connect. 3. Supply your own Judge.me app, then approve. Judge.me needs an OAuth app you register yourself, so bring its client ID and secret. One person does this once for the organization. Credentials are vaulted and nobody, including the AI, reads them back. The connection becomes a toolbox immediately, so you can curate which Judge.me tools are exposed, rename them, or freeze arguments before anyone points a client at it. ## Connect Judge.me to Claude Endpoint: https://api.elaichi.ai/mcp 1. Open Customize, then Connectors. 2. Press Add. 3. Name it, paste the MCP server URL, then Continue. 4. Sign in and approve. On Team and Enterprise, an Owner adds it once. Everyone else turns it on for themselves. ## Connect Judge.me to ChatGPT Endpoint: https://api.elaichi.ai/mcp 1. Open Plugins, then press the + button. 2. Name it and paste the endpoint into Server URL. 3. Leave Authentication on OAuth, then tick the risk acknowledgement. 4. Press Create, then sign in and approve. Works on the web today. The plugin directory lives at chatgpt.com/plugins. ## Connect Judge.me to Cursor Endpoint: https://api.elaichi.ai/mcp 1. Open `~/.cursor/mcp.json`. 2. Add the endpoint under `mcpServers`. 3. Reload Cursor, then sign in and approve. Set up per machine, so repeat it on each computer you work from. ## Connect Judge.me to any MCP client Endpoint: https://api.elaichi.ai/mcp 1. Add the endpoint as a remote MCP server. 2. Sign in and approve. The Elaichi Agent already has these tools, with nothing to set up. ## What the consent screen decides Only Read is granted by default, which is not enough to call a Judge.me tool. Over MCP there is no trusted place to confirm a write in the moment, so the consent screen is the standing approval rather than a formality. Grant Read and Run tools. Think hard before granting Delete, which reaches into connected apps and cannot be undone. ## What teams do with Judge.me through Elaichi ### Find the reviews that need a reply Support. Ask for this week's one and two star Judge.me reviews, read what went wrong, and update each review before the shopper moves on. ### Pull quotes for a product launch Marketing. Ask for the five star reviews on the new range and get the lines worth quoting. Check which featured carousel and preview badge widgets are live so the quotes land on the store too. ### Check review counts and ratings by product Ecommerce. Ask how many reviews a product has and what its rating is, then compare against the rest of the catalog before deciding what to promote. ### See which widgets each page shows Merchandising. List the product reviews, reviews tab, verified badge and all reviews page widgets with their settings, without opening the theme editor. ### Handle a shopper's data request Privacy. When a shopper asks what Judge.me holds about them, look up the reviewer, correct a name or email, and file a data request in one go. ### Know the moment a new review lands Growth. Set up a Judge.me webhook so new reviews reach the team as they arrive, and list the existing webhooks to see what is already in place. ## Frequently asked questions ### How do I connect Judge.me to Claude? Connect Judge.me in Elaichi first, then in Claude open Customize, then Connectors, then Add, and paste https://api.elaichi.ai/mcp. Judge.me needs an app registered inside its own settings, so one person brings the client ID, secret and shop API key from Judge.me once, and that is the only time anyone types a credential. After that, each person signs in as themselves and Claude can work with reviews, reviewers and widgets. ### Does Judge.me work with ChatGPT and Cursor as well as Claude? Yes. Once Judge.me is connected in Elaichi, the same address, https://api.elaichi.ai/mcp, works in Claude, ChatGPT, Cursor, any other MCP client and the Elaichi Agent. You connect Judge.me once and every client sees it. ### What can an AI agent actually do with my Judge.me reviews? It can find Judge.me reviews by product, rating or date, summarize what shoppers are saying, and update a review or a reviewer's details when something needs correcting. It can add a review a customer sent you directly, check review counts and ratings, show which widgets are live on the store and how they are set, and create a webhook so new reviews reach your team. Judge.me has many pieces, so short direct asks like one star reviews this week work better than long paragraphs. ### Does connecting Judge.me give the AI every review and reviewer in my shop? The agent only sees what the person who signed in can see in Judge.me. Elaichi can narrow that further, for example reading reviews but never touching reviewer details, and it can never grant more than Judge.me itself would. Access follows the person, not the connection. ### Can my team share one Judge.me connection? Yes. One person connects Judge.me in Elaichi and shares it with a team, and nobody else ever sees the key or secret. Each teammate still signs in to Elaichi as themselves, so the audit log records who changed which Judge.me review. ### Can I stop an agent from changing reviews in Judge.me? Yes. Restrictions in Elaichi work per action, so you can allow reading Judge.me reviews and widgets while blocking updates to reviews or reviewers and the creation of webhooks. A blocked action is never shown to Claude, ChatGPT or Cursor, so no prompt can reach it. ### What happens to a Judge.me connection when someone leaves? Offboarding that person in Elaichi ends their access to Judge.me through every client at once. A shared Judge.me connection keeps working for everyone else on the team. If you want it gone entirely, disconnecting Judge.me once in Elaichi removes it from Claude, ChatGPT, Cursor and every other client. ## All 34 Judge.me tools Every tool below is callable through https://api.elaichi.ai/mcp once Judge.me is connected, subject to the toolbox it is in and the restrictions on the caller. - **List all Judge.me widgets product reviews** (List). Review Widget is usually placed at the bottom of each product page, displaying all reviews of a product. You can use product handle, external ID, or Judge.me internal ID to specify the product. The upstream spec does not document a response body for this endpoint. - **List all Judge.me widgets preview badges** (List). Preview Badge is usually placed below product titles on product pages or inside product thumbnails on collection pages. This widget display the average star rating and review count of each product. You can use product handle, external ID, or Judge.me internal ID to specify the product. The upstream spec does not document a response body for this endpoint. - **List all Judge.me widgets featured carousels** (List). Reviews Carousel is usually placed on the homepage to showcase specific reviews featured by the store in Judge.me. The upstream spec declares an application/json response but does not document its fields. - **List all Judge.me widgets reviews tabs** (List). Floating Reviews Tab display all product and store reviews via a floating button on any pages in Judge.me. The upstream spec does not document a response body for this endpoint. - **List all Judge.me widgets all reviews pages** (List). All Reviews Page is a dedicated page to showcase all product and store reviews all in one place in Judge.me. The upstream spec declares an application/json response but does not document its fields. - **List all Judge.me widgets verified badges** (List). Verified Reviews Count Badge displays the number of verified published reviews. Stores need at least 20 verified reviews to use this widget in Judge.me. The upstream spec declares an application/json response but does not document its fields. - **List all Judge.me widgets all reviews counts** (List). Return a single total number of product and store reviews in Judge.me. The upstream spec declares an application/json response but does not document its fields. - **List all Judge.me widgets all reviews ratings** (List). Return a single number of average rating of product reviews and store reviews in Judge.me. The upstream spec declares an application/json response but does not document its fields. - **List all Judge.me widgets shop reviews counts** (List). Return a single total number of store reviews in Judge.me. The upstream spec declares an application/json response but does not document its fields. - **List all Judge.me widgets shop reviews ratings** (List). Return a single number of average rating of store reviews in Judge.me. The upstream spec declares an application/json response but does not document its fields. - **List all Judge.me widgets settings** (List). Return widget settings of the shop in HTML format, containing a script tag and a style tag. This carries the widget customization values in Judge.me such as text and colour, which let you render the widget correctly. The upstream spec declares an application/json response but does not document its fields. - **List all Judge.me widgets HTML miracles** (List). Return special HTML that helps show essential parts of widgets before the JS and CSS files are loaded in Judge.me. The upstream spec declares an application/json response but does not document its fields. - **List all Judge.me widgets checkout comments widgets** (List). Return Checkout Comments widget for a product (for Checkout Comments app only). You can use product handle, external ID, or Judge.me internal ID to specify the product. The upstream spec does not document a response body for this endpoint. - **List all Judge.me reviews** (List). Get info of reviews of a product. If product_id is not provided, return all product and store reviews of that store in Judge.me. Returns: id, title, body, rating, pinned, product_external_id, product_title, product_handle, reviewer, source, curated, hidden, and more. - **Create a Judge.me review** (Create). Create a web review in background, similar to submitting a review via the public form on product pages (no authorization required). This endpoint doesn't create any review if the store disables web reviews in Judge.me. The upstream spec does not document a response body for this endpoint. Required: shop_domain, platform, email, name, rating, body. - **Update a Judge.me review by ID** (Update). Publish or hide a Judge.me review via your app interface. For authenticity reason, we don’t support editing reviews via API. Returns: message. Required: id. - **Get single Judge.me review by ID** (Get). Get info of a specific review in Judge.me. Returns: id, title, body, rating, pinned, product_external_id, product_title, product_handle, reviewer, source, curated, hidden, and more. Required: id. - **List all Judge.me reviews counts** (List). Get count of reviews for a specific product or reviewer. If product_id is not provided, return the count of all product and store reviews of that store in Judge.me. The upstream spec does not document a response body for this endpoint. - **Get single Judge.me reviewer by ID** (Get). Get information of the reviewers such as name and email. This is useful when you are building automated flow for users to follow up with reviewers in Judge.me. Returns: reviewer. Required: id. - **Update a Judge.me reviewer by ID** (Update). Create or update a reviewer via your app interface in Judge.me. Returns: reviewer. Required: id. - **Create a Judge.me reviewers data request** (Create). Submit a GDPR-style data request for a reviewer in Judge.me, asking for the data held about a customer and the orders it relates to. Required: customer (with email). - **List all Judge.me webhooks** (List). List all webhooks registered in Judge.me for the shop. Returns: id, failure_count, key, url, created_at, updated_at. - **Create a Judge.me webhook** (Create). Create a webhook in Judge.me: when the event associated with the webhook's key happens, Judge.me sends a POST request to the webhook's url. Returns: shop_id, shop_domain, webhook. - **Get single Judge.me webhook by ID** (Get). Get a single webhook in Judge.me by id. Returns: shop_id, shop_domain, webhook. Required: id. - **Update a Judge.me webhook by ID** (Update). Update a webhook in Judge.me by id. Returns: shop_id, shop_domain, webhook. Required: id. - **Judge.me webhooks bulk delete** (Delete). Delete a Judge.me webhook identified by its event key and url. Returns an empty 204 response on success. - **Create a Judge.me webhooks bulk create** (Create). Bulk Create in Judge.me. The upstream spec does not document a response body for this endpoint. - **List all Judge.me shops info** (List). Get the current Judge.me shop information, including plan, domain and contact details. Returns: id, awesome, country, created_at, currency, custom_domain, dmarc_ok, domain, email, name, onboarding_progress, owner, and more. - **Create a Judge.me shop** (Create). Create a checkout comment in Judge.me. Requires a JSON body; accepts content, external_product_id, create_from (checkout_page or email), and a customer object (first_name, last_name, email, external_id). Only available with the Checkout Comments app. Returns a 200 confirmation; the upstream docs do not document a response body shape. - **Judge.me shops bulk update** (Update). Update the current Judge.me shop's store information. Requires a JSON body with the fields to change — domain, custom_domain, email, owner, phone, name, country, timezone, plan — all optional. Returns a generic success confirmation (success). - **Judge.me shops bulk delete** (Delete). Uninstall a store from Judge.me, removing the shop's Judge.me integration. Takes no parameters. Returns an empty 204 response on success. - **List all Judge.me settings** (List). Get multiple settings values of the store in Judge.me, which can serve as conditions for your app integrations. Returns: settings. - **Create a Judge.me reply** (Create). Create a public reply to a Judge.me review, displayed on the public review widget. Returns an empty success response on 200; if the reply cannot be created, a 422 with an error message is returned. Requires a JSON request body following Judge.me's RequestCreateReply schema. Required: review_id, reply. - **Create a Judge.me private reply** (Create). Create a private email reply to a Judge.me review privately via your app interface. The upstream spec does not document a response body for this endpoint. Required: review_id, private_reply.