How to Use the Userback MCP in LangChain

Q: Can I query past Userback data using LangChain?

Absolutely. You use listfeedbacks to pull historical data into your chain. Since the output is observable via LangSmith, you can trace exactly which pieces of old feedback informed the agent's current decision.

Build complex feedback analysis chains with LangChain.

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 LangChain

Create your Vinkius account to connect Userback to LangChain 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 LangChain

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Analyze Userback data using the MCP Server.

The `list_userback_projects` tool lets you grab a list of all projects. You can then pass that project ID to `get_project_details` so your chain knows exactly what it's working on. This sequence is perfect for initial data gathering in a multi-step reasoning pipeline. Your agent determines the necessary calls, keeping everything observable through LangSmith tracing.

Manage user accounts via MCP Server.

Need to know who submitted feedback? The `list_account_users` tool returns all users associated with your instance. This list feeds directly into subsequent steps, allowing you to filter data based on specific roles or permissions. It’s a quick way for the agent to scope down the search space before calling tools like `get_feedback_details`. You're building context, one tool call at a time.

Build custom feedback reporting with LangChain.

When you combine `list_feedbacks` and `create_feedback_entry`, your agent can build sophisticated reports. First, it pulls all existing data points; then, based on a decision rule, it might create a new record. This multi-step process means the output of fetching old feedback becomes the input for writing new feedback, giving you complete control over the entire workflow.

Setup guide

Set up Userback MCP in LangChain

Prerequisites

Python 3.10+ installed
langchain-mcp-adapters + langgraph packages
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run pip install langchain-mcp-adapters langgraph langchain-openai. The MCP adapters package converts MCP tools into native LangChain BaseTool objects.
2

Connect via HTTP transport
Use MultiServerMCPClient with "transport": "http" pointing to your Vinkius endpoint. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Create a ReAct agent
Pass the discovered tools to create_react_agent() from LangGraph. The agent automatically routes Userback tool calls through the MCP protocol.
4

Run with any LLM
Swap ChatOpenAI for ChatAnthropic, ChatGoogleGenerativeAI, or any LangChain-compatible model. The MCP tools work identically across all providers.

agent.py

from langchain_mcp_adapters.client import MultiServerMCPClient
from langgraph.prebuilt import create_react_agent
from langchain_openai import ChatOpenAI

async with MultiServerMCPClient({
    "userback-mcp": {
        "transport": "http",
        "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp",
    }
}) as client:
    tools = client.get_tools()

    agent = create_react_agent(
        ChatOpenAI(model="gpt-4o"),
        tools,
    )
    result = await agent.ainvoke({
        "messages": "List recent Userback transactions"
    })
    print(result["messages"][-1].content)

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 LangChain

LangChain handles Userback by treating every tool call as a link in your chain. You pass the output of one tool—like project details—to another, letting the agent build complex, multi-step reasoning paths.

The Userback MCP Server primarily deals with user account information, project metadata, and structured feedback records. It manages details about users, projects, and the content of submitted bugs or ideas.

Absolutely. You use `list_feedbacks` to pull historical data into your chain. Since the output is observable via LangSmith, you can trace exactly which pieces of old feedback informed the agent's current decision.

Yes, the client supports aggregating tools from multiple MCP Servers. This means your chain isn't limited to just Userback; you can combine it with other services for a holistic view.

This MCP Server touches user account information, including lists of users. Always ensure your agent handles this sensitive data according to your application's security protocol before passing it through any chain step.

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