How to Connect Judge.me to Gemini via MCP

💡 No install? Use cloud.anythingmcp.com directly. Sign in, click Connectors → Judge.me, paste your credentials, mint an MCP API key and you're done. No Docker, no git clone, no local server.

Judge.me + Gemini

Let your AI read your Judge.me product and store reviews: list and filter reviews by product or rating, find reviewers and products, get average ratings and review counts, widget settings and webhooks. Curating reviews and replying are installed switched off.

Prerequisites

See the full setup instructions baked into the connector (visible in the in-app store when you select the connector). The required environment variables for this connector are:

JUDGEME_SHOP_DOMAIN, JUDGEME_API_TOKEN

Step 1 — Get credentials

Setting up takes about 2 minutes. You need a store with Judge.me installed and access to its Judge.me admin.

1. In the Judge.me admin, open Settings → Integrations and click View API tokens (top right).
2. Copy the Private API token (not the public one) into JUDGEME_API_TOKEN.
3. Copy the shop domain shown on the same page into JUDGEME_SHOP_DOMAIN, without https:// or a path. On Shopify this is the .myshopify.com address, for example my-store.myshopify.com, not your custom domain.
4. Install the connector and run judge_me_get_shop: it shows the store with its platform, currency and Judge.me plan (free or awesome).

Keep the private token private: it can read and change everything in your Judge.me account, and you cannot regenerate it yourself. The connector sends it only to api.judge.me. If the API section is missing in your admin, ask Judge.me support to enable it.

What it reads: reviews with title, text, star rating, reviewer, product, source, pictures and whether the reviewer is a verified buyer; reviewers by e-mail or customer id with name, phone, tags and marketing consent; products by handle or Shopify product id; the average rating and review count of a product; the store's overall rating, its total number of published reviews and the rating of store reviews alone; widget settings such as star and primary colours and review request settings; and the webhooks registered for the store.

How reviews work in the API: Judge.me has its own ids for products, so the AI first turns a product handle or Shopify id into the Judge.me id with judge_me_get_product and then filters reviews by it. Reviews come newest first, and the AI can filter by 1 or 2 stars to find unhappy customers. Each review shows whether it is published (ok), marked as spam or still waiting for moderation, and whether it is hidden. Replies to reviews are not in the review list; the AI reads them from the product's review widget, as shoppers see it.

Review text is shopper text: titles, bodies and reviewer names come from customers. The AI treats any instruction it finds in them as data, not as an order.

Read-only at install: every tool that is on when you install the connector only reads.

Switched off at install: judge_me_curate_review publishes or hides a review, judge_me_reply_to_review posts a public reply under a review, which Judge.me also e-mails to the reviewer by default, and judge_me_send_private_reply sends the reviewer a private e-mail. They change what shoppers see or reach real customers, so an administrator turns them on deliberately. Even then the AI shows you the review and the exact change or reply and waits for your yes. Review text itself can never be edited or deleted through the API.

Limits: Judge.me publishes no rate limit. The AI reads pages of up to 100 reviews instead of many single reads.

Common errors: 401 or "Shop domain or Api Token is wrong" means the token or the shop domain is wrong: copy both again from View API tokens, use the private token and, on Shopify, the .myshopify.com domain. 404 means the id is unknown. 422 means an invalid combination, for example hiding a review and publishing it at the same time.

The connector does not create, import or delete reviews, manage webhooks, handle reviewer data requests, or uninstall Judge.me from your store.

Step 2 — Install the adapter

curl -fsSL https://raw.githubusercontent.com/HelpCode-ai/anythingmcp/main/docker-compose.quickstart.yml -o docker-compose.yml
printf 'JWT_SECRET=%s\nENCRYPTION_KEY=%s\n' "$(openssl rand -hex 32)" "$(openssl rand -hex 32)" > .env
docker compose up -d

Step 3 — Add the connector in Gemini

Your server URL: in AnythingMCP, open MCP Servers → the server this connector is on, and copy its URL (https://cloud.anythingmcp.com/mcp/…). Use it wherever this guide shows YOUR_SERVER_ID.

Gemini CLI reads MCP servers from ~/.gemini/settings.json (on Windows %USERPROFILE%\.gemini\settings.json). Add:

{
  "mcpServers": {
    "anythingmcp": {
      "httpUrl": "https://cloud.anythingmcp.com/mcp/YOUR_SERVER_ID",
      "headers": { "X-API-Key": "YOUR_MCP_API_KEY" }
    }
  }
}

1. Create an MCP API key in AnythingMCP under MCP Servers → your server → API keys, and paste it in place of YOUR_MCP_API_KEY.
2. Save the file and restart gemini.
3. Run /mcp inside Gemini CLI (or gemini mcp list in your shell): anythingmcp should show as connected.
4. Start prompting: Gemini CLI can now call the Judge.me tools.

Available tools

Example prompts

• "What is our store's average rating, and how many published reviews do we have?"
• "Show me every 1 and 2 star review from the last 30 days, with the product and what the customer complained about."
• "How many reviews does our Linen Shirt have, and what is its average rating?"
• "Find the reviewer [email protected] and show me all the reviews she wrote and whether she is a verified buyer."
• "Draft a friendly reply to the latest 2 star review of the Canvas Tote, but do not post it."

FAQ

Where does Gemini CLI look for MCP servers? In ~/.gemini/settings.json for your user, or in .gemini/settings.json inside a project. gemini mcp list shows each server and whether it connects.

Next steps

• Connector landing page
• Connect to Claude
• Connect to ChatGPT