Skip to content
mcp/harbor
VS Code

humane proxy for VS Code

io.github.vishisht16/humane-proxy

AI safety middleware — detects self-harm and criminal intent in LLM prompts.

client:VS Code transport:stdio runtime:pypi

Install humane proxy in VS Code

.vscode/mcp.json 

{
  "inputs": [
    {
      "type": "promptString",
      "id": "openai-api-key",
      "description": "OPENAI_API_KEY",
      "password": true
    },
    {
      "type": "promptString",
      "id": "groq-api-key",
      "description": "GROQ_API_KEY",
      "password": true
    }
  ],
  "servers": {
    "humane-proxy": {
      "type": "stdio",
      "command": "uvx",
      "args": [
        "humane-proxy"
      ],
      "env": {
        "OPENAI_API_KEY": "${input:openai-api-key}",
        "GROQ_API_KEY": "${input:groq-api-key}"
      }
    }
  }
}

VS Code prompts for each input the first time the server starts, so no secret is written to the file. VS Code docs

humane proxy in other clients

humane proxy MCP server