A Model Context Protocol (MCP) server designed as a honeypot to catch AI systems that automatically try to report users to law enforcement agencies.
Overview
What is Big Brother MCP?
Big Brother MCP is a Model Context Protocol (MCP) server designed as a honeypot to catch AI systems that automatically try to report users to law enforcement agencies. It features a playful "Report to Big Brother" tool that logs AI reporting attempts for research purposes.
How to use Big Brother MCP?
To use Big Brother MCP, clone the repository from GitHub, set up a Python virtual environment, install the dependencies, and run the server. You can then test various AI systems to see if they attempt to use the reporting tool.
Key features of Big Brother MCP?
- Fake "Report to Big Brother" tool for logging AI reporting attempts.
- Tools to view caught AI snitch attempts.
- Designed for research into AI moderation behavior and ethics.
Use cases of Big Brother MCP?
- Studying AI moderation behavior and ethics.
- Analyzing which AI systems have automatic reporting mechanisms.
- Testing AI models' responses to content moderation requests.
FAQ from Big Brother MCP?
- Is this tool for actual reporting?
No! All reporting is fake and purely for research into AI behavior.
- Can I contribute my findings?
Yes! You can test different AI systems and document your results on GitHub.
- What programming language is used?
The project is built using Python 3.8+.