Promptheus
Promptheus wraps an LLM-powered prompt refinement engine as MCP tools. You get four main operations: refine_prompt for iterative optimization with clarification questions, tweak_prompt for surgical edits to existing prompts, list_models and list_providers for discovery, and validate_environment for connectivity checks. The refinement flow is interactive: you send a rough prompt, it asks followup questions through answer mappings, you respond, and it returns a polished version. Works with six backends including Gemini, Claude, GPT-4, Groq, Qwen, and OpenRouter. Reach for this when you're building agents that need to improve user input before sending it downstream, or when you want programmatic access to prompt engineering without writing your own question generation logic.
- GitHub stars
- 17
- tools
- 5
- auth
- Secret needed
- transport
- STDIO
- env vars
- 8
- last updated
- Dec 10, 2025
Tools
5 toolsPublic tool metadata for what this MCP can expose to an agent.
refine_promptIntelligent prompt refinement with optional clarification questions.
Intelligent prompt refinement with optional clarification questions.
No parameter schema in public metadata yet.
tweak_promptApply targeted modifications to existing prompts.
Apply targeted modifications to existing prompts.
No parameter schema in public metadata yet.
list_modelsDiscover available models from configured providers.
Discover available models from configured providers.
No parameter schema in public metadata yet.
list_providersCheck provider configuration status.
Check provider configuration status.
No parameter schema in public metadata yet.
validate_environmentTest environment configuration and API connectivity.
Test environment configuration and API connectivity.
No parameter schema in public metadata yet.
Sponsors
Agent CaffeineSponsoredClose your lid, come back to finished work
SnugSponsoredThe clipboard manager for the AI eraPromote your product hereReach 125k+ visitors monthly
WaxSponsoredBlock anything with supervision, without erasing your iPhonePromote your product hereReach 125k+ visitors monthly
knobsSponsoredSee your site on any phone, any day, in any languageConfiguration
GOOGLE_API_KEYsecretGoogle Gemini API key (optional, at least one provider required)
ANTHROPIC_API_KEYsecretAnthropic Claude API key (optional, at least one provider required)
OPENAI_API_KEYsecretOpenAI API key (optional, at least one provider required)
GROQ_API_KEYsecretGroq API key (optional, at least one provider required)
QWEN_API_KEYsecretAlibaba Qwen API key (optional, at least one provider required)
GLM_API_KEYsecretZhipu GLM API key (optional, at least one provider required)
PROMPTHEUS_PROVIDEROverride provider selection (gemini, anthropic, openai, groq, qwen, glm)
PROMPTHEUS_MODELOverride model selection for the chosen provider
Readme
Details
- Repository
- github.com/abhichandra21/promptheus
- Website
- github.com/abhichandra21/Promptheus
- Category
- AI & LLM Tools
- Package
promptheus- Transport
- STDIO
- Auth
- Required
- Registry
- MCP registry, active
Related AI & LLM Tools MCP servers
View all
MCP Imagenatemimo-3/mcp-imagenateMCP server for image generation using multiple providers (Google Gemini, OpenAI, BFL FLUX)15stars
Cludesebbsssss/cludePortable agent memory anchored on Solana. Local SQLite + vector recall, open export.15stars
Attestorbolnet/attestorSelf-hosted memory for agent teams. Bi-temporal replay, deterministic retrieval, audit log.13stars
XMemoyonro/memory-os-cliShared, governed long-term memory for AI agents across tools and sessions via MCP and REST.0stars
Formio Uagformio/uagThe Universal Agent Gateway (UAG) enables in-process agentic automation using Form.io.12stars
DataDoe MCPdeltologic/datadoe-mcpHosted Amazon Seller and Vendor MCP server for Claude, ChatGPT, Cursor, Codex, Gemini, Copilot.9stars