Home › Other › Promptheus

Promptheus

AI-powered prompt refinement with adaptive questioning and multi-provider support (6+ LLM backends)

Python

★ 17 stars Last pushed 2026-03-17 License: MIT

View repository → Website →

Connect

Review any command before running it. Package names and URLs come from the server's own registry entry.

Package (pypi 0.3.1)

uvx promptheus

Or add to your MCP client config:

{
  "mcpServers": {
    "promptheus": {
      "command": "uvx",
      "args": [
        "promptheus"
      ],
      "env": {
        "GOOGLE_API_KEY": "<YOUR_VALUE>",
        "ANTHROPIC_API_KEY": "<YOUR_VALUE>",
        "OPENAI_API_KEY": "<YOUR_VALUE>",
        "GROQ_API_KEY": "<YOUR_VALUE>",
        "QWEN_API_KEY": "<YOUR_VALUE>",
        "GLM_API_KEY": "<YOUR_VALUE>",
        "PROMPTHEUS_PROVIDER": "<YOUR_VALUE>",
        "PROMPTHEUS_MODEL": "<YOUR_VALUE>"
      }
    }
  }
}

GOOGLE_API_KEY secret — Google Gemini API key (optional, at least one provider required)
ANTHROPIC_API_KEY secret — Anthropic Claude API key (optional, at least one provider required)
OPENAI_API_KEY secret — OpenAI API key (optional, at least one provider required)
GROQ_API_KEY secret — Groq API key (optional, at least one provider required)
QWEN_API_KEY secret — Alibaba Qwen API key (optional, at least one provider required)
GLM_API_KEY secret — Zhipu GLM API key (optional, at least one provider required)
PROMPTHEUS_PROVIDER — Override provider selection (gemini, anthropic, openai, groq, qwen, glm)
PROMPTHEUS_MODEL — Override model selection for the chosen provider