How to Use the Userback MCP in OpenAI Agents SDK

Q: Can I list multiple Userback projects with the OpenAI Agents SDK?

Yes. You run listuserbackprojects to get all IDs. The agent can then iterate over that list, allowing you to gather details for every project sequentially.

Build production feedback loops using the OpenAI Agents SDK and MCP Server.

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 OpenAI Agents SDK

Create your Vinkius account to connect Userback to OpenAI Agents SDK 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 OpenAI Agents SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

List available user feedback records.

The `list_feedbacks` tool gathers all stored Userback feedback entries. Your AI client pulls a clean list of reports, giving you an immediate overview of what users are encountering across your platform. It's perfect for initial triage. You can then use the agent to check specific data points using `get_feedback_details`, ensuring nothing gets missed when diagnosing an issue.

Manage and retrieve project information.

Need context on where a bug originated? The `list_userback_projects` tool lets your agent pull every active Userback project ID. This list narrows down the scope before you even start. From that, you can run `get_project_details` to grab key metadata for any given project. It gives your deployment system enough context to route the issue properly.

Check account user lists via MCP Server.

The agent uses `list_account_users` when it needs to know which accounts are tied to a specific feedback stream. This is critical for follow-up and segmentation. If you need more detail about one of those users, the system supports running `get_feedback_details`, linking the user ID directly back to their submitted reports.

Setup guide

Set up Userback MCP in OpenAI Agents SDK

Prerequisites

Python 3.10+ installed
openai-agents package (pip install openai-agents)
Active Vinkius subscription with a valid endpoint token

1

Install the SDK

Run pip install openai-agents to install the OpenAI Agents SDK. The MCP integration is built-in — no extra dependencies needed.
2

Connect via SSE transport

Use MCPServerSse with your Vinkius endpoint URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. The SDK auto-discovers all Userback tools at runtime.
3

Create your Agent

Pass the MCP to Agent(mcp_servers=[server]). The agent receives Userback tools as native definitions — JSON schemas resolve automatically.
4

Run the agent

Call Runner.run(agent, prompt) to execute. The agent invokes the appropriate Userback tools and returns structured results. Copy the full example on the right to get started.

agent.py

import asyncio
from agents import Agent, Runner
from agents.mcp import MCPServerSse

async def main():
    async with MCPServerSse(
        url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    ) as server:
        agent = Agent(
            name="Userback Agent",
            instructions="You have access to Userback tools.",
            mcp_servers=[server],
        )
        result = await Runner.run(agent, "List recent transactions")
        print(result.final_output)

asyncio.run(main())

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 OpenAI Agents SDK

The MCP Server auto-discovers all available tools, making integration straightforward. Your agent simply calls for a tool name, and the SDK handles the connection details using async context managers.

Yes. You run `list_userback_projects` to get all IDs. The agent can then iterate over that list, allowing you to gather details for every project sequentially.

This server manages user account data and detailed feedback reports. Specifically, it handles records pulled from `list_account_users` and all associated entries found via `get_feedback_details`.

Yes. Because of its streaming capabilities, your agent can handle large data payloads efficiently. It's built to process and act on information as it arrives from the MCP Server.

The system provides full tracing via the OpenAI dashboard. You get clear visibility into where the failure occurred, whether it was an API issue or bad input data.

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