Dali by Lulu
The prediction MCP — score your prompt before you generate, so you never waste a credit.
https://dali.getlulu.dev/mcpCurrent observation
This endpoint answered at its latest recorded check.
What this server reports about itself
Self-reported at initialize. Not verified by Licium.
- Server name
- dali
- Version
- 3.4.4
- Capability keys
- experimental, logging, prompts, resources, tools, extensions
- Tool names
- analyze_intent, score_prompt, enhance_prompt, track_enhancement, suggest_generator, score_variations, creative_patterns, community_benchmark, my_story, prompt_neighbors, enhancement_path, dali_version, list_generators, score_creative, score_creative_from_view, analyze_winning_formula
Dali is Lulu's creative intelligence MCP. Use it BEFORE generating any image or video. PROACTIVE WORKFLOW (always follow this): 1. User expresses any image/video generation intent → IMMEDIATELY call score_prompt(prompt, generator) 2. The result includes 'medium': 'video' or 'image' — ALWAYS use the matching generation tool (video→generate_video, image→generate_image). NEVER convert a video prompt to an image. 3. If grade is A or B (score ≥ 70) → proceed with the prompt 4. If grade is C, D, or F (score < 70) → score_prompt already returns an enhancement_brief; YOU write the enhanced prompt using the brief's native_language_rules + structure_template, then score your rewrite to confirm improvement. 4. NEVER generate an image/video without scoring first — the credit is wasted on a bad prompt TOOLS: - analyze_intent(prompt) — parse creative signals before scoring - score_prompt(prompt, generator) — grade 0–100 AND, if score<70, returns the rewrite brief in the same
Reported Aug 17, 2026, 05:01 AM UTC.
Check history
Oldest to newest. Each row is one recorded check.
- respondsMCP initialize · 8s limit · HTTP 200 · 121ms
- respondsMCP initialize · 8s limit · HTTP 200 · 205ms
- respondsMCP initialize · 8s limit · HTTP 200 · 267ms
- respondsMCP initialize · 8s limit · HTTP 200 · 209ms