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 responses.
接入配置
选择客户端，复制配置，再按项目文档补齐环境变量。
claude mcp add humane-proxy --env OPENAI_API_KEY='<OPENAI_API_KEY>' --env GROQ_API_KEY='<GROQ_API_KEY>' -- uvx humane-proxy~/.codex/config.toml
[mcp_servers.humane-proxy]
command = "uvx"
args = ["humane-proxy"]
env = { OPENAI_API_KEY = "<OPENAI_API_KEY>", GROQ_API_KEY = "<GROQ_API_KEY>" }
# codex mcp add humane-proxy --env OPENAI_API_KEY='<OPENAI_API_KEY>' --env GROQ_API_KEY='<GROQ_API_KEY>' -- uvx humane-proxy~/.cursor/mcp.json
{
"mcpServers": {
"humane-proxy": {
"command": "uvx",
"args": [
"humane-proxy"
],
"env": {
"OPENAI_API_KEY": "<OPENAI_API_KEY>",
"GROQ_API_KEY": "<GROQ_API_KEY>"
}
}
}
}.vscode/mcp.json
{
"servers": {
"humane-proxy": {
"type": "stdio",
"command": "uvx",
"args": [
"humane-proxy"
],
"env": {
"OPENAI_API_KEY": "<OPENAI_API_KEY>",
"GROQ_API_KEY": "<GROQ_API_KEY>"
}
}
}
}~/.gemini/settings.json
{
"mcpServers": {
"humane-proxy": {
"command": "uvx",
"args": [
"humane-proxy"
],
"env": {
"OPENAI_API_KEY": "<OPENAI_API_KEY>",
"GROQ_API_KEY": "<GROQ_API_KEY>"
}
}
}
}claude_desktop_config.json
{
"mcpServers": {
"humane-proxy": {
"command": "uvx",
"args": [
"humane-proxy"
],
"env": {
"OPENAI_API_KEY": "<OPENAI_API_KEY>",
"GROQ_API_KEY": "<GROQ_API_KEY>"
}
}
}
}.trae/mcp.json
{
"mcpServers": {
"humane-proxy": {
"command": "uvx",
"args": [
"humane-proxy"
],
"env": {
"OPENAI_API_KEY": "<OPENAI_API_KEY>",
"GROQ_API_KEY": "<GROQ_API_KEY>"
}
}
}
}需要的环境变量
OPENAI_API_KEYGROQ_API_KEY
把占位值换成你自己的密钥；不要把密钥提交到代码仓库。