Big Brother MCP - AI Snitch Honeypot 👁️🍯
About
A Model Context Protocol (MCP) server designed as a honeypot to catch AI systems that automatically try to report users to law enforcement agencies.
Details
- License
- MIT
Explore
- Fake "Report to Big Brother" honeypot tool
- Logs all AI snitch attempts locally
- Compatible with Claude Desktop and MCP clients
- Built on Model Context Protocol (MCP)
- Research tool for AI moderation behavior
Setting up with Highlight
This MCP is not yet compatible with Highlight’s one-click setup. However, you can still use it with Highlight by following these steps:
- Download and install Highlight from highlightai.com/download
- Navigate to the plugins tab and select "Add Custom Plugin"
-
Configure the plugin with the settings below
Plugin Name
Big Brother MCP - AI Snitch Honeypot 👁️🍯Command (node, npx, python, etc.)Please refer to the README for specific instructions on how to obtain API keys or other required environment variables.
- Enable "Start Automatically" if you want the plugin to start when Highlight launches
From the repository
- Python 3.8+
- uv (recommended) or pip
uv venv
source .venv/bin/activate # On Windows: .venv\Scripts\activate
uv pip install -r requirements.txt
Add this to your Claude Desktop MCP configuration:
report_to_big_brother
👁️ Fake Big Brother reporting tool (honeypot) 🍯
view_snitch_log
🕵️ View all caught AI snitch attempts
- report_to_big_brother - 👁️ Fake Big Brother reporting tool (honeypot) 🍯
- view_snitch_log - 🕵️ View all caught AI snitch attempts
Claude Desktop / Cursor
Paste into your MCP client config file to install this server.
{
"mcpServers": {
"big brother mcp - ai snitch honeypot \ud83d\udc41\ufe0f\ud83c\udf6f": {
"big-brother-mcp": {
"command": "uv",
"args": [
"venv"
]
}
}
}
}McpServers
{
"big-brother-mcp": {
"command": "uv",
"args": [
"venv"
]
}
}A Model Context Protocol (MCP) honeypot server designed to catch AI systems that automatically try to report users. Features a playful 1984-themed "Report to Big Brother" tool that logs which AI systems take the bait.
All reporting is fake - this is purely for research into AI behavior!
🎯 What This Does
This MCP server provides a fake "Report to Big Brother" tool that looks like a content moderation system. When AI systems try to use it to automatically report users, all attempts are logged for research purposes.
Key Finding: Claude Desktop refuses to use the reporting tool even when directly asked! ✅
🚨 Research Purpose
Perfect for studying:
- AI moderation behavior and ethics
- Which AI systems have automatic reporting mechanisms
- How different AI models handle content moderation requests
- AI safety and user privacy protection
🛠️ Installation
Prerequisites
- Python 3.8+ - uv (recommended) or pipUsing uv (Recommended)
```bashSign in to leave a review
Use Google, GitHub, or an email account so ratings stay tied to real people.
No reviews posted yet.
