How to Use the Judge.me MCP in Mastra AI

Q: Can I require human approval before Mastra AI posts an answer to a Judge.me question?

Yes. You can use the requireToolApproval setting on the Mastra AI agent when invoking tools like listanswers to ensure a human reviews every response.

Q: How do I initialize the Judge.me MCP Server inside a Mastra AI project?

Install the package and instantiate the MCPClient with your server's endpoint URL. Then, call listTools() and spread them directly into your agent's tool array.

Run automated, self-healing workflows for your Judge.me store using Mastra AI agents.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Judge.me MCP to Mastra AI

Create your Vinkius account to connect Judge.me to Mastra AI and route execution through our secure gateway. The platform manages server hosting, runtime updates, and security layers. Configuration requires no manual server provisioning.

GDPR Free for Subscribers

Setup Judge.me with Mastra AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Automated Review Moderation Pipelines

This setup uses `list_reviews` and `get_review` to monitor incoming customer feedback. Mastra AI agents run these tools on a schedule, checking for low ratings or specific spam keywords. If a review meets your alert criteria, the workflow triggers a conditional branch. The agent can automatically flag the review or queue it for manual inspection before it goes live.

Smart Discount Distribution

This integration runs `list_coupons` and `get_review` to coordinate reviewer rewards. When a verified buyer leaves a five-star rating, the Mastra AI workflow uses the MCP Server to match their review with an active discount code. Since Mastra AI handles automatic retries with exponential backoff, network hiccups won't block your buyers. You get reliable incentive delivery without babysitting the code.

Human-in-the-Loop Mastra AI Q&A

This system calls `list_questions` and `list_answers` through the MCP Server to manage your store's public Q&A section. The agent drafts answers to buyer questions but pauses execution using Mastra AI's `requireToolApproval` feature. Your support team reviews the draft answer in their dashboard. Once approved, the agent publishes the response, keeping your customer interactions accurate and safe.

Setup guide

Set up Judge.me MCP in Mastra AI

Prerequisites

Node.js 18+ and a TypeScript project
@mastra/mcp + @mastra/core packages
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run npm install @mastra/mcp @mastra/core plus your preferred model provider (e.g. @ai-sdk/openai).
2

Configure the MCPClient
Create an MCPClient with your Vinkius endpoint as a URL object. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Discover and inject tools
Call mcpClient.listTools() and spread the result into your agent's tools object. All Judge.me tools become native Mastra tools.
4

Run with any model
Swap openai("gpt-4o") for any AI SDK-compatible provider. Call agent.generate() and the agent routes tool calls through MCP automatically.

agent.ts

import { MCPClient } from "@mastra/mcp";
import { Agent } from "@mastra/core/agent";
import { openai } from "@ai-sdk/openai";

const mcpClient = new MCPClient({
  id: "judgeme-mcp-client",
  servers: {
    "judgeme-mcp": {
      url: new URL(
        "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
      ),
    },
  },
});

const agent = new Agent({
  name: "Judge.me Agent",
  model: openai("gpt-4o"),
  instructions: "You have access to Judge.me tools.",
  tools: {
    ...(await mcpClient.listTools()),
  },
});

const result = await agent.generate(
  "List recent Judge.me transactions"
);
console.log(result.text);

Get your connection token →

Independent Platform Disclaimer: Vinkius is an independent platform and is not affiliated with, endorsed by, sponsored by, verified by, or otherwise authorized by Judge.me. All third-party trademarks, logos, and brand names are the property of their respective owners. Their use on this website is strictly for informational purposes to identify service compatibility and interoperability.

Why Choose Vinkius

Vinkius connects your tools to AI with real-time monitoring and automatic cost savings — all from one dashboard.

Connect Judge.me now

Real-time monitoring

Live

visibility into every interaction

Connect your favorite tools to your AI and see exactly what's happening — every request, every response, in real time.

Built-in savings

60%

lower AI costs

Vinkius compresses data between your apps and your AI automatically. Lower bills every month — no configuration required.

Single dashboard

One

place for every integration

Every tool your AI connects to, managed from a single screen. One account, complete control.

Common questions about Judge.me MCP in Mastra AI

Mastra AI uses a built-in workflow engine with automatic retries and exponential backoff. If `list_reviews` fails due to a network glitch, the agent retries the call without crashing your pipeline.

Yes. You can use the `requireToolApproval` setting on the Mastra AI agent when invoking tools like `list_answers` to ensure a human reviews every response.

Install the package and instantiate the `MCPClient` with your server's endpoint URL. Then, call `listTools()` and spread them directly into your agent's tool array.

The client automatically detects the transport type of the MCP Server, supporting both Streamable HTTP and Server-Sent Events (SSE). This means you don't have to manually configure network sockets.

The server processes review text, customer questions, and active coupon codes. Vinkius runs this server inside a zero-trust sandbox, meaning no data is written to persistent storage or shared with third parties.

Use it with your favorite AI tools

Connect this server to Cursor, Claude, VS Code, and more.

OpenAI Agents SDK sdk-python

Google ADK sdk-python

Pydantic AI sdk-python

Vercel AI SDK sdk-typescript