Clarifyprompt
Turns vague prompts into platform-specific syntax for 60+ AI tools across image generation (Midjourney, DALL-E, Stable Diffusion), video (Sora, Runway), audio (ElevenLabs), and coding assistants (Claude, Cursor). Exposes MCP tools that read workspace context files (CLAUDE.md, .cursorrules, package.json), resolve user intent, then rewrite your input with the right parameters, aspect ratios, quality flags, and structure for whichever platform you're targeting. Ships with an eval harness and runs over stdio. Reach for this when you're switching between creative AI tools and don't want to memorize each platform's prompt syntax or manually append --ar 16:9 --style raw every time you generate an image.
- GitHub stars
- 5
- tools
- 5
- auth
- Secret needed
- transport
- STDIO
- env vars
- 3
- last updated
- Mar 12, 2026
Tools
5 toolsPublic tool metadata for what this MCP can expose to an agent.
optimize_promptThe main tool. Optimizes a prompt for a specific AI platform.
The main tool. Optimizes a prompt for a specific AI platform.
No parameter schema in public metadata yet.
clarify_with_userGiven an ambiguous draft prompt, returns 1–3 targeted clarifying questions instead of guessing.
Given an ambiguous draft prompt, returns 1–3 targeted clarifying questions instead of guessing.
No parameter schema in public metadata yet.
ground_promptStrict, retrieval-augmented variant of optimize_prompt; caller-provided sources are pinned at the highest priority so the rewrite is grounded in the material provided.
Strict, retrieval-augmented variant of optimize_prompt; caller-provided sources are pinned at the highest priority so the rewrite is grounded in the material provided.
No parameter schema in public metadata yet.
critique_promptLLM-as-judge that scores a candidate prompt 0–10 across 6 default dimensions and, when below threshold, returns an improved rewrite.
LLM-as-judge that scores a candidate prompt 0–10 across 6 default dimensions and, when below threshold, returns an improved rewrite.
No parameter schema in public metadata yet.
compose_promptThe canonical pipeline: one call runs clarify, ground/optimize, critique, and optional auto-revise.
The canonical pipeline: one call runs clarify, ground/optimize, critique, and optional auto-revise.
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
LLM_API_URL*LLM API endpoint URL (OpenAI-compatible or Anthropic)
LLM_API_KEYsecretAPI key for the LLM provider (not needed for local Ollama)
LLM_MODEL*Model name/ID to use for optimization
Readme
ClarifyPrompt MCP
A context-aware MCP prompt compiler that transforms vague prompts into platform-optimized prompts for 60+ AI platforms across 7 categories — grounded in your workspace signals (CLAUDE.md, AGENTS.md, .cursorrules, package.json), resolved intent, and the capabilities of the target model.
Details
- Repository
- github.com/lumabyteco/clarifyprompt-mcp
- Category
- AI & LLM Tools
- Package
clarifyprompt-mcp- Transport
- STDIO
- Auth
- Required
- Registry
- MCP registry, active
Related AI & LLM Tools MCP servers
View all
Image Recognition Mcpmcp-s-ai/image-recognition-mcpMCP server for AI-powered image recognition and description using OpenAI vision models.5starsImage Recongnition Mcpmcp-s-ai/image-recongnition-mcpMCP server for AI-powered image recognition and description using OpenAI vision models.5stars
Skill Historypineapple-farm/skill-historyTrack download history for 70,000+ agent skills. Search and get daily snapshots.5stars
Moltbridgesagemindai/moltbridgeAgent network intelligence for AI agents. Trust scoring, broker discovery, and Ed25519 identity.5stars
Throngletsshangri-la-0428/throngletsP2P shared memory substrate for AI agents — stigmergic knowledge network via libp2p5stars
TigerGraphtigergraph/tigergraph-mcpExplore and evolve TigerGraph schemas, run GSQL and Cypher, load data, and search vector embeddings.5stars