Clarifyprompt-MCP

An MCP server that transforms vague prompts into platform-optimized prompts for 58 AI platforms across 7 categories. Send a raw prompt. Get back a version specifically optimized for Midjourney, DALL-E, Sora, Runway, ElevenLabs, Claude, ChatGPT, or any of the 58 supported platforms — with the right syntax, parameters, and structure each platform expects.

→ LumabyteCo/clarifyprompt-mcp · listed on glama

Is this your MCP?

Claim it to get a verified publisher badge, a free copy of our full audit findings, and direct contact for any high-priority issues we find.

Install from

Glama

M8ven verifies MCPs across every public registry — install directly from whichever one you prefer.

// key findings

✅

No credential exfiltration, no sensitive file access, no obfuscation

Static analysis found nothing flowing your secrets to unexpected places.

✅

Open source with a license and README

Anyone can audit the code, the license is declared, and the publisher documents what it does.

🔐

You'll be asked for 5 credentials: EMBED_API_KEY, LLM_API_KEY, OLLAMA_API_KEY, SEARCH_API_KEY, TAVILY_API_KEY

These are read from process.env at runtime. Make sure you trust where they’ll be sent.

// required environment variables

This server reads these from process.env. You'll be asked to provide them before it can run.

configCLARIFYPROMPT_SUPPRESS_LEGACY_WARN— No Set to 1 to silence the one-line deprecation hint when CLARIFYPROMPT_CONFIG_DIR / CLARIFYPROMPT_DATA_DIR are used.

🔐 secretEMBED_API_KEY— No (1.3.0+) Embedding API key. Defaults to LLM_API_KEY when unset; not needed for local Ollama.

configEMBED_API_URL— No (1.3.0+) Embedding endpoint for memory + knowledge-pack retrieval. Any OpenAI-compatible /v1/embeddings endpoint. Defaults to LLM_API_URL when unset — Ollama users just work.

configEMBED_DIMENSION— No (1.3.0+) Embedding output dimension. Default: 768. Must match your embedding model (1536 for OpenAI text-embedding-3-small, 1024 for Voyage, etc.).

configEMBED_MODEL— No (1.3.0+) Default: nomic-embed-text:v1.5 (768-dim, pull with ollama pull nomic-embed-text). Swap to text-embedding-3-small for OpenAI, voyage-3 for Voyage, embed-english-v3.0 for Cohere.

🔐 secretLLM_API_KEY— Depends API key (not needed for local Ollama)

configLLM_API_URL— "": "http://localhost:11434/v1",

configLLM_MODEL— "": "qwen2.5:7b"

configLLM_TIMEOUT_MS— env-var override on the LLM client. Default stays at 30s; users on slow hosted models can bump it. The eval workflow uses 120s for gpt-4o-mini.

🔐 secretOLLAMA_API_KEY

configOLLAMA_API_URL

🔐 secretSEARCH_API_KEY— No API key for the configured SEARCH_PROVIDER. Not needed for self-hosted SearXNG.

configSEARCH_API_URL— No Search endpoint URL. Only needed for self-hosted SearXNG (point at your instance).

configSEARCH_PROVIDER— No Optional web-search enrichment provider when enrich_context: true. One of tavily (default) \ brave \ serper \ serpapi \ exa \ searxng.

🔐 secretTAVILY_API_KEY

configXDG_DATA_HOME

// full audit trail

The full breakdown of what we checked, the deductions that landed, the network hosts, the dependency advisories, and concrete fix guidance is available to verified publishers.

// improvement guidance — verified publishers only

We have 6 concrete improvements we can share with the publisher of this MCP. Each comes with specific guidance to raise the trust score.

// embed badge in your README

[![M8ven Score](https://m8ven.ai/badge/mcp/lumabyteco-clarifyprompt-mcp-1c8jd7)](https://m8ven.ai/mcp/lumabyteco-clarifyprompt-mcp-1c8jd7)

commit: 87a9ec5e7008ea595762b7aaba4fdeb488154dc9

code hash: 213446ade1b66e4e092f905963a05f251c6f6dbb4b8bec7268afe26710248782

verified: 6/12/2026, 11:32:47 AM

view raw JSON →