How to Use the Userback MCP in Mastra AI

Q: How does Mastra AI handle creating a Userback feedback entry?

Your agent calls createfeedbackentry. If the system rejects the data, your workflow engine handles the failure gracefully. It might retry the submission or escalate it to an admin.

Q: Can I use Mastra AI to list Userback projects?

Absolutely. The listuserbackprojects tool gives you a clean array of all available project IDs, which your workflow can then iterate over.

Q: What is the process for checking existing user data with Mastra AI and Userback?

You first run listaccountusers to see who exists. Then, if you need specific details on a report, your agent can use getfeedbackdetails for deep context.

Q: When calling the MCP Server, what data type is handled by Userback?

This server deals with structured feedback entries, containing bug reports and visual evidence. The workflow engine treats this as a key piece of operational data.

Q: Does Mastra AI support listing all Userback feedbacks in a complex flow?

Yes, the agent can run listfeedbacks to pull all submissions. You'll need to build branching logic around this list to determine next steps.

Build complex feedback workflows that retry and handle failure using Mastra AI.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Userback MCP to Mastra AI

Create your Vinkius account to connect Userback 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 Userback with Mastra AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Structured Feedback Collection

The `create_feedback_entry` tool lets you automatically log a new bug report into Userback. If the initial entry fails, your agent can retry the action with different parameters or notify an admin user. Use this in multi-step workflows where capturing feedback is just one crucial step among many automated tasks.

Retrieving Project Context for Workflows

When a workflow needs to know which project the bug belongs to, use `get_project_details`. This ensures your agent has all the required context before proceeding. It's perfect for conditional branching based on project status. If you need multiple projects, run `list_userback_projects` first; then the workflow can select the right one.

Monitoring Account Users and Feedbacks

Your agent needs visibility into who's using the system. You can use `list_account_users` to check all active accounts, or run `list_feedbacks` to gather a comprehensive list of reported issues. This allows your workflow engine to automatically triage and route feedback submissions based on account roles.

Setup guide

Set up Userback 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 Userback 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: "userback-mcp-client",
  servers: {
    "userback-mcp": {
      url: new URL(
        "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
      ),
    },
  },
});

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

const result = await agent.generate(
  "List recent Userback 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 Userback. 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 Userback 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 Userback MCP in Mastra AI

Your agent calls `create_feedback_entry`. If the system rejects the data, your workflow engine handles the failure gracefully. It might retry the submission or escalate it to an admin.

Absolutely. The `list_userback_projects` tool gives you a clean array of all available project IDs, which your workflow can then iterate over.

You first run `list_account_users` to see who exists. Then, if you need specific details on a report, your agent can use `get_feedback_details` for deep context.

This server deals with structured `feedback entries`, containing bug reports and visual evidence. The workflow engine treats this as a key piece of operational data.

Yes, the agent can run `list_feedbacks` to pull all submissions. You'll need to build branching logic around this list to determine next steps.

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