Judge.me MCP server for AI agents and assistants

Securely connect your AI agents and chatbots (Claude, ChatGPT, Cursor, etc) with Judge.me MCP or direct API to read reviews, search customer feedback, reply to shoppers, and manage review requests through natural language.

Judge.me logoJudge.me
Oauth2

Judge.me is a product and shop review platform for online stores. It helps merchants collect, manage, and display trusted customer feedback.

34 Tools

Try Judge.me now

Type what you want done — sign in and watch it run live in the Tool Router playground.

TOOL ROUTER PLAYGROUND
Judge.me
Try asking
TOOLS

Supported Tools

Every Judge.me action and event your agent gets out of the box.

Bulk Create Webhooks

Create multiple webhook subscriptions in one request.

Bulk Update Review Visibility

Sequentially publish, hide, archive, or unarchive 1-25 reviews.

Count Reviews

Count management review records, optionally filtered by reviewer, product, and star rating.

Count Storefront Reviews

Return the storefront aggregate review count for either all product and shop-level reviews or only shop-level reviews.

Create Checkout Comment

Persist a customer's comment for a product through Judge.

Create Private Review Reply

Create a private reply to a review and, by default, email it to the reviewer.

Create Public Review Reply

Post a public reply to a review and optionally email it to the reviewer.

Create Review

Submit a public web review in the background; no review is created when the shop disables web reviews.

Create Webhook

Create one webhook subscription for a Judge.

Delete Webhook

Delete the webhook subscription matching its current Judge.

Get All Reviews Page Widget

Return rendered HTML for one page of the shop's all-reviews page.

Get Checkout Comments Widget

Return rendered Checkout Comments widget HTML for one product; requires the Checkout Comments app.

Get Current Shop

Return identity, plan, platform, owner, and widget metadata for the OAuth-connected shop.

Get Featured Reviews Carousel

Return the rendered HTML for the shop's featured-reviews carousel.

Get Product

Return a product by Judge.

Get Product Preview Badge

Return the rendered rating-and-review-count badge HTML for one product.

Get Product Review Widget

Return the rendered review-widget HTML for one product and, optionally, one review page.

Get Review

Return one review by its Judge.

Get Reviewer

Return a reviewer by Judge.

Get Reviews Rating

Return the average rating for all product and shop-level reviews or for shop-level reviews only.

Get Reviews Tab Widget

Return the rendered floating reviews-tab HTML for a selected review type and page.

Get Settings

Return values for one or more named Judge.

Get Verified Reviews Badge

Return the rendered verified-review-count badge, or null when the shop has fewer than 20 verified reviews.

Get Webhook

Return one webhook subscription by its Judge.

Get Widget Placeholder HTML

Return the rendered placeholder HTML used before Judge.

Get Widget Settings HTML

Return the shop's rendered widget customization script and style HTML, not structured setting values.

List Reviews

Return one page of reviews, optionally filtered by reviewer, product, rating, published-only state, or reviewer email.

List Webhooks

Return all webhook subscriptions configured for the connected shop.

Request Reviewer Data

Submit a reviewer data request for a customer email and one or more external order IDs.

Uninstall Shop

WARNING: This uninstalls Judge.

Update Current Shop

Update selected profile and commerce metadata for the OAuth-connected shop.

Update Review Visibility

Publish, hide, archive, or unarchive a review.

Update Webhook

Replace a webhook subscription's event key and callback URL.

Create or Update Reviewer

Create or update a reviewer selected by Judge.

SETUP GUIDE

Connect Judge.me MCP Tool with your Agent

1

Install Composio

typescript
npm install @composio/core ai @ai-sdk/mcp @ai-sdk/openai
Install the Composio SDK and your agent framework
2

Create a session with MCP enabled

typescript
import { Composio } from "@composio/core";

const composio = new Composio();
const { mcp } = await composio.create("your-user-id", {
  toolkits: ["judge_me"],
  mcp: true,
});
Create a session scoped to Judge.me and read its MCP URL and headers
3

Connect your agent to the MCP server

typescript
import { createMCPClient } from "@ai-sdk/mcp";
import { openai } from "@ai-sdk/openai";
import { generateText, stepCountIs } from "ai";

const client = await createMCPClient({
  transport: { type: "http", url: mcp.url, headers: mcp.headers },
});

const { text } = await generateText({
  model: openai("gpt-5.6-sol"),
  tools: await client.tools(),
  prompt: "List recent reviews for my store",
  stopWhen: stepCountIs(10),
});

console.log(text);
await client.close();
Pass the session's MCP URL and headers to your agent and run a Judge.me request
SETUP GUIDE

Connect Judge.me API Tool with your Agent

1

Install Composio

typescript
npm install @composio/core @composio/openai openai
Install the Composio SDK, the OpenAI provider, and the OpenAI SDK
2

Create a Composio session

typescript
import OpenAI from "openai";
import { Composio } from "@composio/core";
import { OpenAIResponsesProvider } from "@composio/openai";

const composio = new Composio({ provider: new OpenAIResponsesProvider() });
const client = new OpenAI();

const session = await composio.create("your-user-id", { toolkits: ["judge_me"] });
const tools = await session.tools();
Initialize Composio with the OpenAI Responses provider and create a session scoped to Judge.me
3

Run Judge.me tools with your agent

typescript
let response = await client.responses.create({
  model: "gpt-5.6-sol",
  tools,
  input: [{ role: "user", content: "List recent reviews for my store" }],
});

while (response.output.some((o) => o.type === "function_call")) {
  const outputs = await composio.provider.handleToolCalls(session, response.output);
  response = await client.responses.create({
    model: "gpt-5.6-sol",
    tools,
    previous_response_id: response.id,
    input: outputs,
  });
}

console.log(response.output_text);
Send a request, execute the Judge.me tool calls through the session, and print the final answer

Why Use Composio?

AI Native Judge.me Integration

  • Supports both Judge.me MCP and direct API based integrations
  • Structured, LLM-friendly schemas for reliable tool execution
  • Rich coverage for reading, writing, and querying your Judge.me data

Managed Auth

  • Built-in OAuth handling with automatic token refresh and rotation
  • Central place to manage, scope, and revoke Judge.me access
  • Per user and per environment credentials instead of hard-coded keys

Agent Optimized Design

  • Tools are tuned using real error and success rates to improve reliability over time
  • Comprehensive execution logs so you always know what ran, when, and on whose behalf

Enterprise Grade Security

  • Fine-grained RBAC so you control which agents and users can access Judge.me
  • Scoped, least privilege access to Judge.me resources
  • Full audit trail of agent actions to support review and compliance

Rolling this out across your team?

Give your team centralized access control across every framework with Composio’s MCP Gateway.

EXPLORE MCP GATEWAY
FAQ

Frequently asked questions

Judge.me requires connections to go through your own OAuth app. You register it once with Judge.me, add its client ID and secret in the Composio dashboard, and from then on everyone connects by signing in to Judge.me as usual. Composio handles the rest of the flow and the token refresh.

Yes! Composio's Tool Router enables agents to use multiple toolkits. Learn more.

Yes. Composio is SOC 2 Type II compliant and is built to keep your Judge.me connection and credentials secure. OAuth tokens and API keys are encrypted, and sensitive customer data is protected at rest and in transit.

Composio also undergoes independent security testing and continuously monitors its systems for security threats. You can review the latest reports and policies in the Composio Trust Center.

Composio maintains and updates all toolkit integrations automatically, so your agents always work with the latest API versions.

When you connect a Judge.me account through Composio, every action runs under that account, so anything the agent creates, sends, or changes shows up in Judge.me as done by you. Keep an approval step in your prompt for actions with side effects, such as sending or deleting, and have the agent draft first.

Exactly the ones Judge.me lists on its consent screen when you connect. Review that screen before approving. If you connect a work account, your Judge.me administrator may need to approve the app first, and you can revoke the access inside Judge.me whenever you want.

Yes. Composio supports multiple connected accounts for the same app, and that works in Claude, ChatGPT, or any other assistant you connect through Composio. Give each Judge.me connection a name such as work or personal, and the assistant uses the one you mention in the request. Each account keeps its own credentials and nothing is merged.

Composio refreshes Judge.me tokens automatically, so day to day you do nothing. If you revoke access inside Judge.me, or Judge.me invalidates the session, the connection shows as expired in Composio and the agent stops acting on that account until you reconnect it, which is a single sign-in.

Composio's free Hobby plan includes 100,000 tool calls per month with no credit card, which covers most personal Judge.me use. Paid plans add higher limits and team features. Your Judge.me plan and its API limits still apply as usual.

Built-in connectors usually give one AI access to a limited set of apps. Many people use Composio because it lets their AI connect to more apps than it normally supports, or connect to multiple accounts for the same app (e.g. connect Claude to multiple Judge.me accounts).

With Composio, you connect Judge.me once and then use it across different AI assistants without setting it up separately in each one. Connect your apps to Composio once, then connect Composio to whichever AI you use, whether that's Claude, ChatGPT, Hermes, or your own custom assistant.

Start with Judge.me.It takes 30 seconds.

Managed auth, hosted MCP servers, and every Judge.me tool your agent needs.Free to start.

Start building