AI-powered prompt refinement with adaptive questioning and multi-provider support (6+ LLM backends)
io.github.abhichandra21/promptheus
https://github.com/abhichandra21/Promptheus
STDIO
No auth required
How models use it and what it is built for.
AI-powered prompt refinement with adaptive questioning and multi-provider support (6+ LLM backends)
Hosted endpoint — paste into any MCP client.
Configuration this server reads at startup.
Google Gemini API key (optional, at least one provider required)
Anthropic Claude API key (optional, at least one provider required)
OpenAI API key (optional, at least one provider required)
Groq API key (optional, at least one provider required)
Alibaba Qwen API key (optional, at least one provider required)
Zhipu GLM API key (optional, at least one provider required)
Override provider selection (gemini, anthropic, openai, groq, qwen, glm)
Override model selection for the chosen provider
Where to find authoritative docs and source for Promptheus.
MCP Playground runs 10,000+ hosted MCP servers — GitHub, Linear, Notion, Stripe, Sentry and more — across Claude, GPT, Gemini, DeepSeek and 30+ AI models. Compare model answers side-by-side, save agent presets, share runs. Zero install.
Open Agent Studio