Create Survey

io.github.feedbk-aiPublished by GitHub account feedbk-aiv1.0.0Updated Oct 24, 2026

Create AI surveys with dynamic follow-up probing directly from your AI assistant.

VerifiedStreamable HTTPWeb executableProductivity & WorkflowData & Analytics

Overview

AI-generated overview

A remote MCP server that lets an assistant design, publish and analyze AI-moderated surveys and interviews through the feedbk survey-builder agent.

What you can do
Create, edit and preview AI-moderated surveys and interviews from a natural-language description, with automatic question-type setup and AI follow-up probing. Publish or close surveys and get shareable interview links for participants. Analyze survey results. Continue a conversation by passing the session_id returned in the previous response.
When to use it
Useful when you want to draft customer satisfaction, user research or employee feedback surveys conversationally and publish them for real respondents without leaving the assistant.
Requirements
A remote endpoint at mcp.feedbk.ai over streamable HTTP; no package, environment variables or headers are declared. The README notes that ChatGPT use requires a Pro, Team, Enterprise or Edu subscription, and that only the remote endpoint can auto-deploy surveys and return shareable links.
Before you install
The server can publish and close surveys and generate participant-facing links, so changes affect live data. Sessions expire after an hour of inactivity. Survey content and responses are handled by the third-party feedbk service.

Installation

In SourceWeft

  1. Open Create Survey in the dashboard and add it to a workspace.
  2. Enable the server for the chats that should use its tools.

Web executable via Streamable HTTP. Remote servers run from the web runtime once configured in a workspace.

Use with an agent

Paste this prompt into Claude Code, Codex, Cursor or another agent — or into SourceWeft chat. The agent reads this server's install guide, shows you its publisher, endpoint and sign-in, and adds it to your client once you agree. Keys never go into a command.

Read https://sourceweft.com/mcp/io.github.feedbk-ai%2Fcreate-survey/install.md and connect the MCP server it describes to my client. Before changing any config, show me its publisher, endpoint and sign-in method and wait for my OK. Never put an API key in a command or in a file I would commit; ask me where it should come from.

Read the install guide the agent follows

Other MCP clients

Add this to your client's mcpServers config.

{
  "mcpServers": {
    "create-survey": {
      "type": "http",
      "url": "https://mcp.feedbk.ai/mcp"
    }
  }
}

README

[feedbk.ai logo]

AI-Moderated Interviews & Surveys via MCP

[Website] [Docs] [MIT License] [Python 3.10+]

Create smarter surveys with AI-moderated interviews and intelligent follow-up probing — directly from your AI assistant.


Why Feedbk MCP?

Feedbk MCP brings AI interview/survey creation directly into your workflow:

  • ✅ Natural language interview design — just describe what you need
  • ✅ Automatic question type detection and configuration
  • ✅ Built-in AI probing for deeper insights
  • ✅ Create and share interview links with participants instantly

Local vs Remote: Choose Your Workflow

FeatureLocal InstallRemote (mcp.feedbk.ai)
Create interview guides✅✅
Export guides✅✅
Auto-deploy to feedbk.ai❌✅
Get shareable interview links❌✅

Installation

Claude Code
sh
claude mcp add --transport http feedbk https://mcp.feedbk.ai/mcp
VS Code

Add to your VS Code MCP settings:

json
"mcp": {  "servers": {    "feedbk": {      "type": "http",      "url": "https://mcp.feedbk.ai/mcp"    }  }}
Claude Desktop

Navigate to Settings → Connectors → Add Custom Connector, then enter:

  • Name: Feedbk
  • URL: https://mcp.feedbk.ai/mcp
OpenAI ChatGPT

Requires ChatGPT Pro, Team, Enterprise, or Edu subscription

  1. Go to Settings → Connectors
  2. Enable Developer Mode under Advanced settings
  3. Click Create and enter:
    • Name: Feedbk
    • Server URL: https://mcp.feedbk.ai/mcp
  4. In a new chat, click + → More → Developer Mode and enable Feedbk
Google Gemini CLI
sh
gemini mcp add feedbk --url https://mcp.feedbk.ai/mcp
OpenAI Codex CLI
sh
codex mcp add feedbk --url https://mcp.feedbk.ai/mcp

Usage

Just ask your AI assistant to create an interview:

Create a customer satisfaction survey about our mobile app
Build a user research interview to understand why users cancel their subscriptions
Design an employee feedback survey about remote work preferences

The skill will guide you through:

  1. Interview Name — What are you calling this survey?
  2. Purpose — Why are you conducting this? (one sentence)
  3. Questions — What do you want to ask?

Question Types

AI Probing

Feedbk's AI interviewer automatically asks intelligent follow-up questions based on responses — no manual configuration needed.

Single-Choice

"What is your preferred method of communication?"Options: Email / Phone / Text / Video Call

Multiple-Choice

"Which features do you use? (Select all)"Options: Dashboard / Reports / Analytics / Integrations

Open-Ended Text

"What's your biggest challenge with our product?"Response: Free text

Rating (Likert Scale)

"How satisfied are you with our service?"Scale: 1 (Very Dissatisfied) → 5 (Very Satisfied)

Connect with Us


License

MIT

Source: README.md at commit 384980f

Tools

1

survey_builder

Send a message to the feedbk survey-builder agent. It can create, edit, preview, publish, close, and analyze AI-moderated surveys. Omit session_id on the first call; pass the session_id from the previous response on follow-up calls to continue the conversation (sessions expire after an hour of inactivity).

Parametersmessagerequiredsession_id

Version history

1
  1. v1.0.0LatestSep 16, 2026

Score

100% of the applicable checks met

How complete this listing is, computed from the registry entry, the endpoint and public sources. Not a rating of the server and not a statement that it is safe or working today: reachability is a dated check, and no installs or reviews go into the score.

  • Reached in the last 30 daysRequired25 pts
  • Auth declaredRequired10 pts
  • Tools listedRequired15 pts
  • DescriptionRequired15 pts
  • Logo10 pts
  • Documentation15 pts
  • License10 pts