Promptheus is an MCP server that provides prompt refinement capabilities for LLMs through intelligent questioning and modifications. It supports multiple AI providers and offers both CLI and web UI interfaces.
From the registry: AI-powered prompt refinement with adaptive questioning and multi-provider support (6+ LLM backends)
$ pip install promptheusPlease install the `promptheus` MCP server into my current AI client (that's you).
Required prerequisites (do these first if not already done):
- **Install promptheus** — Install with MCP support and configure at least one LLM provider API key Run: `pip install promptheus`
Canonical MCP server config (stdio transport):
- command: `promptheus`
- args: ["mcp"]
- optional environment variables:
- `GOOGLE_API_KEY`: Google Gemini API key (example: `<your-google-api-key>`)
- `ANTHROPIC_API_KEY`: Anthropic Claude API key (example: `<your-anthropic-key>`)
- `OPENAI_API_KEY`: OpenAI API key (example: `<your-openai-key>`)
- `GROQ_API_KEY`: Groq API key (example: `<your-groq-key>`)
Note: Prompt refinement and optimization MCP. At least one provider API key required. 5 tools: refine_prompt, tweak_prompt, list_models, list_providers, validate_environment.
Add this MCP server to my current client's config in the correct format for you. If you need secrets or credentials I haven't provided, ASK me — do not invent values or leave raw placeholders. After adding it, tell me how to verify the server is connected.GOOGLE_API_KEYrequiredAPI key for Google provider.ANTHROPIC_API_KEYrequiredAPI key for Anthropic provider.OPENAI_API_KEYrequiredAPI key for OpenAI provider.AI Agents Framework with Self Reflection and MCP support