User Feedback MCP

User Feedback MCP

Enable seamless human-in-the-loop feedback for model-driven workflows.

50
Stars
9
Forks
50
Watchers
1
Issues
User Feedback MCP is a simple Model Context Protocol (MCP) server designed to facilitate human-in-the-loop workflows within tools such as Cline and Cursor. It allows applications, especially desktop software undergoing development, to request and incorporate user feedback before finalizing AI-assisted tasks. The system integrates with existing development pipelines and provides customizable configuration through a .user-feedback.json file and a web-based interface for easy interaction.

Key Features

MCP-compliant feedback server
Integration with Cline and Cursor
Configurable user feedback prompts
Web-based UI for feedback submission
.user-feedback.json configuration support
Automated or manual command execution
Multi-step workflow support
Easy installation with uv
Customizable server settings for development tools
Support for testing interactive desktop applications

Use Cases

Collecting end-user feedback during software development
Integrating human decision points into AI-driven workflows
Testing and refining desktop applications with user interactions
Enabling feedback loops before task completion in automation tools
Improving prompt engineering through real-time user input
Facilitating model-assisted development with human validation
Automating workflow steps while gating on user approval
Configuring interactive sessions for complex tasks in IDEs
Building and evaluating multi-step command sequences with feedback
Supporting rapid prototyping of AI features with human oversight

README

User Feedback MCP

Simple MCP Server to enable a human-in-the-loop workflow in tools like Cline and Cursor. This is especially useful for developing desktop applications that require complex user interactions to test.

Screenshot showing the feedback UI

Prompt Engineering

For the best results, add the following to your custom prompt:

Before completing the task, use the user_feedback MCP tool to ask the user for feedback.

This will ensure Cline uses this MCP server to request user feedback before marking the task as completed.

.user-feedback.json

Hitting Save Configuration creates a .user-feedback.json file in your project directory that looks like this:

json
{
  "command": "npm run dev",
  "execute_automatically": false
}

This configuration will be loaded on startup and if execute_automatically is enabled your command will be instantly executed (you will not have to click Run manually). For multi-step commands you should use something like Task.

Installation (Cline)

To install the MCP server in Cline, follow these steps (see screenshot):

Screenshot showing installation steps

  1. Install uv globally:
    • Windows: pip install uv
    • Linux/Mac: curl -LsSf https://astral.sh/uv/install.sh | sh
  2. Clone this repository, for this example C:\MCP\user-feedback-mcp.
  3. Navigate to the Cline MCP Servers configuration (see screenshot).
  4. Click on the Installed tab.
  5. Click on Configure MCP Servers, which will open cline_mcp_settings.json.
  6. Add the user-feedback-mcp server:
json
{
  "mcpServers": {
    "github.com/mrexodia/user-feedback-mcp": {
      "command": "uv",
      "args": [
        "--directory",
        "c:\\MCP\\user-feedback-mcp",
        "run",
        "server.py"
      ],
      "timeout": 600,
      "autoApprove": [
        "user_feedback"
      ]
    }
  }
}

Development

sh
uv run fastmcp dev server.py

This will open a web interface at http://localhost:5173 and allow you to interact with the MCP tools for testing.

Available tools

<use_mcp_tool>
<server_name>github.com/mrexodia/user-feedback-mcp</server_name>
<tool_name>user_feedback</tool_name>
<arguments>
{
  "project_directory": "C:/MCP/user-feedback-mcp",
  "summary": "I've implemented the changes you requested."
}
</arguments>
</use_mcp_tool>

Star History

Star History Chart

Repository Owner

mrexodia
mrexodia

User

Repository Details

Language Python
Default Branch main
Size 184 KB
Contributors 1
License MIT License
MCP Verified Nov 12, 2025

Programming Languages

Python
100%

Tags

Topics

cline cursor mcp mcp-server modelcontextprotocol

Join Our Newsletter

Stay updated with the latest AI tools, news, and offers by subscribing to our weekly newsletter.

We respect your privacy. Unsubscribe at any time.

Related MCPs

Discover similar Model Context Protocol servers

  • MCP-Human

    MCP-Human

    Enabling human-in-the-loop decision making for AI assistants via the Model Context Protocol.

    MCP-Human is a server implementing the Model Context Protocol that connects AI assistants with real human input on demand. It creates tasks on Amazon Mechanical Turk, allowing humans to answer questions when AI systems require assistance. This solution demonstrates human-in-the-loop AI by providing a bridge between AI models and external human judgment through a standardized protocol. Designed primarily as a proof-of-concept, it can be easily integrated with MCP-compatible clients.

    • 20
    • MCP
    • olalonde/mcp-human
  • interactive-mcp

    interactive-mcp

    Enable interactive, local communication between LLMs and users via MCP.

    interactive-mcp implements a Model Context Protocol (MCP) server in Node.js/TypeScript, allowing Large Language Models (LLMs) to interact directly with users on their local machine. It exposes tools for requesting user input, sending notifications, and managing persistent command-line chat sessions, facilitating real-time communication. Designed for integration with clients like Claude Desktop and VS Code, it operates locally to access OS-level notifications and command prompts. The project is suited for interactive workflows where LLMs require user involvement or confirmation.

    • 313
    • MCP
    • ttommyth/interactive-mcp
  • Webvizio MCP Server

    Webvizio MCP Server

    Bridge between Webvizio feedback and AI coding agents via the Model Context Protocol

    Webvizio MCP Server is a TypeScript-based server implementing the Model Context Protocol to securely and efficiently interface with the Webvizio API. It transforms web page feedback and bug reports into structured, actionable developer tasks, providing AI coding agents with comprehensive task context and data. It offers methods to fetch project and task details, retrieve logs and screenshots, and manage task statuses. The server standardizes communication between Webvizio and AI agent clients, facilitating automated issue resolution.

    • 4
    • MCP
    • Webvizio/mcp
  • Jupyter MCP Server

    Jupyter MCP Server

    Real-time, context-aware MCP server for managing and interacting with Jupyter Notebooks.

    Jupyter MCP Server is an implementation of the Model Context Protocol (MCP) designed to enable AI-driven, real-time management and interaction with Jupyter Notebooks. It offers context-aware capabilities, smart execution features, and multimodal output handling, seamlessly integrating with JupyterLab and supporting multiple notebooks simultaneously. The server is compatible with any MCP client and can work with local or hosted Jupyter deployments.

    • 765
    • MCP
    • datalayer/jupyter-mcp-server
  • Homebrew MCP Python Server

    Homebrew MCP Python Server

    Expose Homebrew management as MCP tools for integration with AI clients.

    Homebrew MCP Python Server provides an MCP-compliant interface to manage Homebrew packages on macOS via a Python-based server. It enables standardized control of Homebrew commands through the Model Context Protocol, supporting integration with Claude Desktop, Cursor, and other MCP-compatible clients. The server operates via stdio using JSON-RPC 2.0, logs all interactions, and offers a declarative Python implementation. It is designed for seamless tool-chaining, advanced context management, and easy integration into LLM-driven environments.

    • 18
    • MCP
    • jeannier/homebrew-mcp
  • locust-mcp-server

    locust-mcp-server

    Run Locust load tests via Model Context Protocol integration.

    locust-mcp-server provides a Model Context Protocol (MCP) server for executing Locust load tests, allowing seamless connection between Locust and AI-powered development environments. It offers easy configuration, real-time test output, and both headless and UI testing modes. The project features a simple API for customizable load testing scenarios and supports various runtime and user parameters.

    • 9
    • MCP
    • QAInsights/locust-mcp-server
  • Didn't find tool you were looking for?

    Be as detailed as possible for better results