MCPLow riskUnclaimed

humane-proxy

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

Vishisht16vishisht16/humane-proxy★ 28Updated Jul 6, 2026

server.json

{
  "$schema": "https://static.modelcontextprotocol.io/schemas/2025-09-29/server.schema.json",
  "name": "io.github.Vishisht16/humane-proxy",
  "description": "AI safety middleware — detects self-harm and criminal intent in LLM prompts.",
  "repository": {
    "url": "https://github.com/Vishisht16/Humane-Proxy",
    "source": "github"
  },
  "version": "0.6.0",
  "packages": [
    {
      "registryType": "pypi",
      "identifier": "humane-proxy",
      "version": "0.6.0",
      "transport": {
        "type": "stdio"
      },
      "packageArguments": [
        {
          "value": "mcp-serve",
          "type": "positional",
          "valueHint": "command"
        }
      ],
      "environmentVariables": [
        {
          "description": "OpenAI API key for Stage 3 reasoning (optional)",
          "isSecret": true,
          "name": "OPENAI_API_KEY"
        },
        {
          "description": "Groq API key for LlamaGuard Stage 3 (optional)",
          "isSecret": true,
          "name": "GROQ_API_KEY"
        }
      ]
    }
  ]
}

Permissions

DeclaredDetected
Runs code—python
Installs—pypi:humane-proxy@0.6.0
Runs install scripts—None
NetworkNoneNone
Needs credentialsGROQ_API_KEYOPENAI_API_KEYGROQ_API_KEYOPENAI_API_KEY
Outside the workspace—None
Agent tools—None

Checks

Low risk · Nothing worth a warning was found.

Not reviewed by a person · Checked by rules; the model review is not switched on yet.

Versions

  1. #10.6.0latestOct 7, 2026