Interactive Feedback MCP server for AI agents

This Node.js implementation of the Interactive Feedback MCP provides a modern web-based interface for human-in-the-loop AI workflows, helping to reduce premium tool calls and improve collaboration between users and AI assistants.

Installation

Prerequisites

Make sure you have Node.js 18.0.0 or higher installed:

# Check Node.js version
node --version
# Should output v18.0.0 or higher

# Check npm version
npm --version
# Should output 8.0.0 or higher

Installation Steps

# 1. Clone the repository
git clone https://github.com/zivhdinfo/interactive-feedback-mcp-nodejs.git
cd interactive-feedback-mcp-nodejs

# 2. Install dependencies
npm install

# 3. Test installation
node server.js
# Should output: MCP Server listening on stdio

Configuration

For Cursor IDE

Add to Cursor settings.json:

{
  "mcpServers": {
    "interactive-feedback-mcp": {
      "command": "node",
      "args": [
        "C:\\path\\to\\interactive-feedback-mcp-nodejs\\server.js"
      ],
      "env": {
        "NODE_ENV": "production"
      }
    }
  }
}

Note: Update the path in args to match your installation directory.

For Claude Desktop

Add to Claude Desktop config:

Windows: %APPDATA%\Claude\claude_desktop_config.json
macOS: ~/Library/Application Support/Claude/claude_desktop_config.json
Linux: ~/.config/Claude/claude_desktop_config.json

{
  "mcpServers": {
    "interactive-feedback-mcp": {
      "command": "node",
      "args": [
        "/path/to/interactive-feedback-mcp-nodejs/server.js"
      ],
      "env": {
        "NODE_ENV": "production"
      }
    }
  }
}

For Cline / Windsurf

Use the same configuration format as above. Configure the server in the respective tool's MCP settings with interactive-feedback-mcp as the server identifier.

Usage

Basic Workflow

AI Assistant calls tool: AI uses interactive_feedback tool
Web UI opens: Browser automatically opens with feedback interface
Review project: View project directory and prompt from AI
Run commands (optional): Execute commands to test/verify
Provide feedback: Enter feedback for AI assistant
Submit: Send feedback and close UI

Available Tool

`interactive_feedback`

Parameters:

project_directory (string): Path to the project directory
summary (string): Summary of the request or context

Returns:

command_logs (string): Output from executed commands
interactive_feedback (string): User feedback for the AI

Example Usage

// AI assistant calls this tool
{
  "tool": "interactive_feedback",
  "arguments": {
    "project_directory": "/path/to/project",
    "summary": "Need feedback on the new feature implementation"
  }
}

When to Use Interactive Feedback

Critical Actions (Always Required)

Before making significant code changes
Before running system commands
Before build/deploy operations
Before package management
Before major refactoring
When encountering errors
Before finalizing responses

Recommended Actions

When requirements are unclear
Before creating new files
When multiple solution approaches exist
Before making breaking changes
When working with sensitive data

Troubleshooting

Common Issues

Port conflicts: Server uses fixed port 3636 (ensure it's available)
Permission errors: Ensure Node.js has proper permissions
Browser not opening: Check default browser settings
WebSocket connection failed: Verify firewall settings

Debug Mode

# Enable debug logging
DEBUG=* node server.js

How to install this MCP server

For Claude Code

To add this MCP server to Claude Code, run this command in your terminal:

claude mcp add-json "interactive-feedback-mcp" '{"command":"node","args":["server.js"],"cwd":"C:\\path\\to\\interactive-feedback-mcp-nodejs","env":{"NODE_ENV":"production"}}'

See the official Claude Code MCP documentation for more details.

For Cursor

There are two ways to add an MCP server to Cursor. The most common way is to add the server globally in the ~/.cursor/mcp.json file so that it is available in all of your projects.

If you only need the server in a single project, you can add it to the project instead by creating or adding it to the .cursor/mcp.json file.

Adding an MCP server to Cursor globally

To add a global MCP server go to Cursor Settings > Tools & Integrations and click "New MCP Server".

When you click that button the ~/.cursor/mcp.json file will be opened and you can add your server like this:

{
    "mcpServers": {
        "interactive-feedback-mcp": {
            "command": "node",
            "args": [
                "server.js"
            ],
            "cwd": "C:\\path\\to\\interactive-feedback-mcp-nodejs",
            "env": {
                "NODE_ENV": "production"
            }
        }
    }
}

Adding an MCP server to a project

To add an MCP server to a project you can create a new .cursor/mcp.json file or add it to the existing one. This will look exactly the same as the global MCP server example above.

How to use the MCP server

Once the server is installed, you might need to head back to Settings > MCP and click the refresh button.

The Cursor agent will then be able to see the available tools the added MCP server has available and will call them when it needs to.

You can also explicitly ask the agent to use the tool by mentioning the tool name and describing what the function does.

For Claude Desktop

To add this MCP server to Claude Desktop:

1. Find your configuration file:

macOS: ~/Library/Application Support/Claude/claude_desktop_config.json
Windows: %APPDATA%\Claude\claude_desktop_config.json
Linux: ~/.config/Claude/claude_desktop_config.json

2. Add this to your configuration file:

{
    "mcpServers": {
        "interactive-feedback-mcp": {
            "command": "node",
            "args": [
                "server.js"
            ],
            "cwd": "C:\\path\\to\\interactive-feedback-mcp-nodejs",
            "env": {
                "NODE_ENV": "production"
            }
        }
    }
}

3. Restart Claude Desktop for the changes to take effect