Parse a creative prompt into structured intent dimensions.

Returns: detected camera language, motion, lighting, style, mood signals, identified gaps, and which models suit the current signals best.

Score a prompt for a specific generation model (0–100).

Returns a ScoreCard: overall score, letter grade (A–F), per-dimension breakdown, what's missing, detected anti-patterns, and a one-line verdict on whether it's safe to generate.

Supported models: veo3, seedance, kling, runway, wan, minimax, higgsfield, sora, flux, midjourney, ideogram, firefly, imagen Aliases: "veo" → veo3, "mj" → midjourney, "sd" → flux, "gen4" → runway, "hailuo" → minimax

Rewrite a prompt using AI to score higher on the target model.

Returns a rewrite brief — YOU (the LLM) write the enhanced prompt from it.

Dali provides creative intelligence: what's missing, the model's native language rules, structure template, priority fixes, and length target. You provide creative execution: actually writing the better prompt.

Community graph intelligence: which patterns consistently produce high-grade prompts for this model?

Powered by the Dali V3 graph brain — every prompt scored by every Dali user contributes to this. The more community usage, the richer the signal.

Also returns: enhancement unlocks (which patterns added during enhance_prompt have produced the highest score gains for this model).

Compare your prompt against community top scorers for this model.

Scores your prompt, then queries the Dali graph to find:

• Which A-grade community patterns are absent from your prompt

• Which enhancement patterns would give you the biggest score gain

• Where you sit vs the community average for this model

Your Dali creative intelligence report.

Shows your prompt scoring history across all models:

• Total prompts scored + this month's count

• Average score and model breakdown

• Grade distribution (how many A, B, C, D, F scores)

• Your creative DNA: patterns that define your highest-scoring work (V3 graph)

• A personal insight on where you'd improve fastest

Requires login at dali.getlulu.dev. History is tied to your GitHub account.

List all supported generation models with medium, creator, and core strength.

Score a prompt AND get an AI-enhanced version in one call.

Combines score_prompt + enhance_prompt into a single round-trip. Returns: original score, enhanced prompt, and new score — so you can see the exact improvement before deciding which version to use.

Record a before/after enhancement pair in the Dali graph.

Call this after you've written an enhanced prompt using the rewrite brief from enhance_prompt. This trains the community graph with real A/B data — contributing to creative_patterns and community_benchmark for all users.

Pick the best generation model for a creative concept + budget.

Analyzes the concept (motion, style, realism requirements) and returns a ranked list of generators with rationale and estimated cost per generation.

Score multiple prompt variations for the same generator in one call.

Returns a ranked list — highest to lowest score — so you can immediately see which variation to send to generation. Best used after writing 2–5 candidate prompts and wanting to pick the winner objectively.

Return the current Dali server version and changelog.

Useful for checking if your MCP is connected to the latest server, or for debugging version mismatches between the pip package and hosted API.