AI safety middleware — detects self-harm and criminal intent in LLM prompts.
Runs locally over stdio
This server isn't hosted — your MCP client launches it from a package registry. Use one of the commands below, or drop the config into your client (e.g. Claude Desktop).
Run
uvx humane-proxy
MCP client config
{
"mcpServers": {
"humane-proxy": {
"command": "uvx",
"args": [
"humane-proxy"
]
}
}
}