AI Surveys via MCP ->

AI-Moderated Interviews & Surveys via MCP

A guide to creating surveys with AI probing using the Model Context Protocol (MCP) in Claude Code and other AI assistants.

Dr. Andreas Ejupi

Dr. Andreas Ejupi

AI Research

This article explains how to create surveys directly from your AI assistant using the Model Context Protocol (MCP).

What is MCP?

The Model Context Protocol (MCP) is an open standard by Anthropic. It defines how AI assistants can communicate with external systems.

The concept is comparable to USB: Just as USB provides a unified interface for hardware, MCP provides a unified interface for AI applications. Developers can build MCP servers that provide specific functionality — in this case, creating surveys.

Learn more about MCP →

How does it work?

The Feedbk MCP server provides the following functions:

  • Create surveys — via text description in natural language
  • Configure question types — open questions, multiple choice, scales
  • Enable AI probing — automatic follow-up questions for unclear answers
  • Generate links — for sharing with participants

Communication runs through the AI assistant. You describe what you want to know, and the MCP server handles the technical implementation.

Installation

Claude Code

claude mcp add --transport http feedbk https://mcp.feedbk.ai/mcp

Claude Desktop

  1. Navigate to Settings → Connectors → Add Custom Connector
  2. Enter the following details:
    • Name: Feedbk
    • URL: https://mcp.feedbk.ai/mcp
  3. Click Save and start creating interviews

Other MCP Clients

Use the following endpoint:

  • URL: https://mcp.feedbk.ai/mcp
  • Transport: HTTP

See also our GitHub Repository

Usage

In Claude Code you can start the workflow with:

/feedbk:create_interview

The MCP skill guides you through the interview creation process:

  1. Interview Name — What should the survey be called?
  2. Purpose — What is it about? (one sentence)
  3. Questions — What do you want to know?
Claude Code
MCP Dialog in Claude Code

The AI creates the survey and generates a shareable link for your participants.

In Claude Desktop, after adding the connector, you start by clicking on the + symbol and selecting the “Create Interview” prompt from Feedbk. The AI assistant then guides you through the interview drafting process.

Claude Desktop
MCP Dialog in Claude Desktop

At the end, you have the option to create the interview and receive a shareable link immediately.

Use Cases

The MCP feature is particularly suited for quickly creating and sharing surveys — similar to SurveyMonkey or similar platforms, but directly in your AI assistant.

Typical use cases:

  • Event feedback — collect opinions after events
  • Customer satisfaction — run quick pulse checks
  • Course and workshop feedback — gather participant responses

MCP is still a relatively new standard, so integration is not yet available in all tools. It works particularly well with Anthropic products like Claude Code and Claude Desktop.

Follow our blog for more updates, e.g. on AgentSkills — another standard for standardized workflows like creating or analyzing surveys.