Record · mcp-feedbackMCP serverCosts not checkedRecord checked Sep 23, 2026

MCP Feedback Enhanced

Pause an AI coding agent to collect your feedback in a web UI or desktop app before it finishes.

Visit MCP Feedback Enhanced →View repository

Sources and review

Checked against public documentation on September 23, 2026. Suitability guidance is our editorial judgment; this is not a performance benchmark or an endorsement.

Repository and README

Best for

Keeping a human checkpoint in long agent sessions so fewer requests are spent on wrong turns.

Avoid if

You would run a version older than 2.6.1, which fixed an unauthenticated command-execution flaw and WebSocket hijacking; command execution has since been removed.

About MCP Feedback Enhanced

MCP Feedback Enhanced adds an interactive feedback step to AI-assisted development: the agent calls a tool that opens a web interface or desktop application where you review its work, add text or images and steer the next step. It is an enhanced fork of an earlier feedback server and detects local, SSH and WSL environments.

MCP Feedback Enhanced is listed in this index written primarily in JavaScript, with 3.8k stars on GitHub. Its latest recorded repository push was in October 2026; that is not an ASE editorial review date.

Before connecting: access and data

This record's specific permissions have not been reviewed by ASE. Read the publisher's documentation before copying setup or connecting.

List the accounts, files and services the enabled tools can read, change or execute. Check your actual credentials and discovered tools.
Use narrowly scoped credentials and read-only mode where supported. Review proposed writes before approving them; a generated configuration does not apply these limits for you.
Local launch is not local-only data processing. External services receive requests, and your client may pass tool results to its model provider. Check both destinations before sharing private data.
Keep keys and browser session files out of shared config, repositories and screenshots. Know how to disconnect the server and separately revoke its credentials or account sessions.

Read the setup guide →

Add MCP Feedback Enhanced to your MCP client

Generated from the launch command in the project's README. Your client starts the server on demand.

Claude CodeRun in your terminal

claude mcp add mcp-feedback-enhanced -- uvx mcp-feedback-enhanced@latest

Cursor~/.cursor/mcp.json or .cursor/mcp.json

{
  "mcpServers": {
    "mcp-feedback-enhanced": {
      "command": "uvx",
      "args": ["mcp-feedback-enhanced@latest"]
    }
  }
}

VS Code.vscode/mcp.json

{
  "servers": {
    "mcp-feedback-enhanced": {
      "type": "stdio",
      "command": "uvx",
      "args": ["mcp-feedback-enhanced@latest"]
    }
  }
}

Claude Desktopclaude_desktop_config.json

{
  "mcpServers": {
    "mcp-feedback-enhanced": {
      "command": "uvx",
      "args": ["mcp-feedback-enhanced@latest"]
    }
  }
}

Codex~/.codex/config.toml

[mcp_servers.mcp-feedback-enhanced]
command = "uvx"
args = ["mcp-feedback-enhanced@latest"]

Check the project's README for required accounts, keys and permissions before connecting. Setup guide for each client →

For agent buildersMake your product part of the discovery.Explore advertising