by Vishisht16 · MCP Server · ★ 29
🛡️ HumaneProxy Lightweight, plug-and-play AI safety middleware that protects humans. HumaneProxy sits between your users and any LLM. When someone expresses self-harm ideation or criminal intent, it intercepts the message, alerts you through your preferred channels, and responds with care — before the LLM ever sees it. What it does 🆘 Self-harm detected → Blocked with international crisis resources. Operator notified. ⚠️ Cri
| Stars | 29 |
| Forks | 31 |
| Language | Python |
| Category | MCP Server |
| License | Apache-2.0 |
| Quality Score | 72.6801974806477/100 |
| Open Issues | 4 |
| Last Updated | 2026-07-07 |
| Created | 2026-03-17 |
| Platforms | mcp, python |
| Est. Tokens | ~19k |
Explore other popular mcp server tools:
Humane-Proxy is Lightweight AI safety middleware that protects humans by intercepting self-harm and criminal intent in LLM prompts. Features a 3-stage safety pipeline, MCP server for agents, and automated care respon. It is categorized as a MCP Server with 29 GitHub stars.
Humane-Proxy is primarily written in Python. It covers topics such as ai-safety, crime-prevention, guardrails.
You can find installation instructions and usage details in the Humane-Proxy GitHub repository at github.com/Vishisht16/Humane-Proxy. The project has 29 stars and 31 forks, indicating an active community.
Humane-Proxy is released under the Apache-2.0 license, making it free to use and modify according to the license terms.