npm package discovery and stats viewer.

Discover Tips

  • General search

    [free text search, go nuts!]

  • Package details

    pkg:[package-name]

  • User packages

    @[username]

Sponsor

Optimize Toolset

I’ve always been into building performant and accessible sites, but lately I’ve been taking it extremely seriously. So much so that I’ve been building a tool to help me optimize and monitor the sites that I build to make sure that I’m making an attempt to offer the best experience to those who visit them. If you’re into performant, accessible and SEO friendly sites, you might like it too! You can check it out at Optimize Toolset.

About

Hi, 👋, I’m Ryan Hefner  and I built this site for me, and you! The goal of this site was to provide an easy way for me to check the stats on my npm packages, both for prioritizing issues and updates, and to give me a little kick in the pants to keep up on stuff.

As I was building it, I realized that I was actually using the tool to build the tool, and figured I might as well put this out there and hopefully others will find it to be a fast and useful way to search and browse npm packages as I have.

If you’re interested in other things I’m working on, follow me on Twitter or check out the open source projects I’ve been publishing on GitHub.

I am also working on a Twitter bot for this site to tweet the most popular, newest, random packages from npm. Please follow that account now and it will start sending out packages soon–ish.

Open Software & Tools

This site wouldn’t be possible without the immense generosity and tireless efforts from the people who make contributions to the world and share their work via open source initiatives. Thank you 🙏

© 2026 – Pkg Stats / Ryan Hefner

mcp-feedback-enhanced

v0.1.66

Published

MCP Feedback Enhanced Server - Interactive feedback collection for AI assistants

Readme

MCP Feedback Enhanced Server

Version: 0.1.66

MCP Server component that connects to the VSCode Extension's WebSocket server to collect user feedback.

Architecture

┌─────────────────┐         ┌─────────────────┐
│   Cursor/AI     │  stdio  │   MCP Server    │
│   (AI Client)   │ ←────→  │   (This)        │
└─────────────────┘         └────────┬────────┘
                                     │ WebSocket
                                     ▼
                            ┌─────────────────┐
                            │ VSCode Extension│
                            │   (WS Server)   │
                            └────────┬────────┘
                                     │
                                     ▼
                            ┌─────────────────┐
                            │ Feedback Panel  │
                            │   (Webview)     │
                            └─────────────────┘

How It Works

  1. Extension starts → Creates WebSocket server → Writes ~/.config/mcp-feedback-enhanced/servers/<pid>.json
  2. MCP Server starts → Waits for interactive_feedback call
  3. AI calls tool → MCP Server reads server files → Finds matching Extension by workspace path → Connects
  4. User submits → Feedback flows back to AI

Server Discovery

MCP Server finds the correct Extension using priority-based matching:

| Priority | Strategy | Description | |----------|----------|-------------| | 1 | CURSOR_TRACE_ID | Same Cursor window (environment variable) | | 2 | Exact workspace | project_directory in server's workspaces array | | 3 | Prefix match | Project is inside a workspace directory | | 4 | parentPid | Same parent process (backward compatibility) | | 5 | Single server | Only one server running | | 6 | Most recent | Last registered server by timestamp |

Tools

interactive_feedback

Collect feedback from user through the VSCode sidebar panel.

{
  project_directory: string;  // Project path for context & server matching
  summary: string;            // AI summary for user review
  timeout?: number;           // Timeout in seconds (default: 600)
}

get_system_info

Returns system environment information.

Configuration

Add to ~/.cursor/mcp.json:

{
  "mcpServers": {
    "mcp-feedback-enhanced": {
      "command": "node",
      "args": ["/path/to/mcp-server/dist/index.js"],
      "env": {
        "MCP_FEEDBACK_DEBUG": "true"
      },
      "timeout": 89400,
      "autoApprove": ["interactive_feedback"]
    }
  }
}

Environment Variables

| Variable | Default | Description | |----------|---------|-------------| | MCP_FEEDBACK_DEBUG | false | Enable debug logging to stderr |

Debug Mode

Set MCP_FEEDBACK_DEBUG=true to see:

  • Server discovery process
  • WebSocket connection status
  • Message flow between components

Troubleshooting

"No MCP Feedback Extension found for project"

  1. Ensure VSCode extension is installed and activated
  2. Open the MCP Feedback panel (click sidebar icon)
  3. Check ~/.config/mcp-feedback-enhanced/servers/ for server files
  4. Verify your project path is in the workspaces array

Connection timeout

  1. Check if Extension's WebSocket server is running (port in server file)
  2. Verify no firewall blocking localhost connections
  3. Try reloading the Cursor window

License

MIT