Lulu-The-Narwhal/dali-mcp

Creative intelligence MCP — score your prompt before you spend the credit

About dali-mcp

dali.getlulu.dev  ·  Install  ·  Live stats  ·  Lulu

The prediction MCP that helps you avoid the AI generation tax.

Most AI generation failures are prompt failures. You can't tell the difference until after you've burned the token. Dali scores your prompt before you generate — so you never waste a credit on a bad prompt again. Every wasted generation has a real cost (a Seedance retry is ~$6) — the live dashboard tracks what the community has saved by catching bad prompts before they burned a credit.

- Install - Tools - Supported models - Platform supersets - Why model-specific? - MCP resources - Contributing

Hosted MCP — connect once, scores every prompt:

Tool What it does ------------------- scoreprompt(prompt, model) Grade 0–100, letter grade, per-dimension breakdown, what's missing, verdict enhanceprompt(prompt, model) Returns a structured rewrite brief — YOUR LLM writes the enhanced prompt using it scoreandenhance(prompt, generator) Score + enhance in one round-trip — returns original score, enhanced prompt, and new score trackenhancement(original, enhanced, generator) Record a before/after pair in the graph brain — trains community patterns suggestgenerator(concept, budgetusdmax) Pick the best model for your concept + budget constraint scorevariations(prompts, generator) Rank a list of prompt variants in one call — returns them highest to lowest score daliversion() Server version + changelog analyzeintent(prompt) Parse dimensions: camera, motion, lighting, style, mood, gaps creativepatterns(model) Community top patterns for this model

From the project README.

Maintaining this server?

Add the radar badge to your README — it shows your project was picked up by MCP Radar and links to this page:

[![On MCP Radar](https://mcp.liqiwa.com/badge.svg)](https://mcp.liqiwa.com/s/Lulu-The-Narwhal--dali-mcp.html)

Related MCP servers