MCP Radar
MCP Server

Dali by Lulu

io.github.Lulu-The-Narwhal/dali
Design & Creative Marketing & Advertising Public & reachable MCP 2025-11-25

What this MCP does

Scores and improves creative prompts and advertising images using generation-target analysis, community patterns, performance benchmarks, and winner-versus-loser ad data.

Capabilities

Tools

16 tools
analyze_intent
Parse a creative prompt into structured intent dimensions.
Read only
Input schema 
{'type': 'object', 'required': ['prompt'], 'properties': {'medium': {'type': 'string', 'default': 'auto'}, 'prompt': {'type': 'string'}}, 'additionalProperties': False}
Output schema 
{'type': 'object', 'additionalProperties': True}
analyze_winning_formula
Find YOUR winning ad formula from your own numbers — paste your ads export. The category prior is a cold-start fallback; the real signal is what wins in YOUR account. Paste an ads CSV (a creative image-URL column + a performance column — CPA / CTR / ROAS / purchases) and Dali runs vision on your winners vs losers and returns the attributes that separate them, plus how your account compares to the industry median. If an email is supplied, the formula is saved and emailed with a ready-to-paste Claude prompt wired to Dali — so scoring the next creative is one step. Returns: formula — attributes over-represented in your winners (value, winner%/loser%, lift) benchmark — your median vs the vertical's industry median (when category given) analyzed — how many winners/losers were read, and the metric direction saved — whether the lead+formula were captured (only when email supplied)
Read only
Input schema 
{'type': 'object', 'required': ['csv'], 'properties': {'csv': {'type': 'string'}, 'email': {'type': 'string', 'default': ''}, 'category': {'type': 'string', 'default': ''}}, 'additionalProperties': False}
Output schema 
{'type': 'object', 'additionalProperties': True}
community_benchmark
Compare your prompt against community top scorers for this generator. Returns your score, missing A-grade patterns, and highest-ROI patterns to add.
Read only
Input schema 
{'type': 'object', 'required': ['prompt', 'generator'], 'properties': {'prompt': {'type': 'string'}, 'generator': {'type': 'string'}}, 'additionalProperties': False}
Output schema 
{'type': 'object', 'additionalProperties': True}
creative_patterns
Community graph: which patterns consistently produce high-grade prompts for this generator? Powered by the V3 graph brain (Supabase PostgreSQL). Every scored prompt contributes. Returns top patterns by type, enhancement unlocks, and cross-model universal patterns.
Read only
Input schema 
{'type': 'object', 'required': ['generator'], 'properties': {'grade': {'type': 'string', 'default': 'A'}, 'generator': {'type': 'string'}}, 'additionalProperties': False}
Output schema 
{'type': 'object', 'additionalProperties': True}
dali_version
Current Dali MCP version and changelog. Check this whenever you want to know what tools are available, what changed in the latest release, or which version is running.
Read only
Input schema 
{'type': 'object', 'properties': {}, 'additionalProperties': False}
Output schema 
{'type': 'object', 'additionalProperties': True}
enhancement_path
Show the most reliable path from a bad grade to an A on this generator. Mines the Dali graph for all F/D → A/B enhancement pairs and surfaces the patterns that appear most consistently in the 'after' side. These are the highest-ROI moves for this specific generator. Use this when: - A prompt just scored D or F and you're not sure what to fix - You want to know which improvements matter most for a specific generator - You want to understand generator-specific enhancement strategy
Read only
Input schema 
{'type': 'object', 'required': ['generator'], 'properties': {'generator': {'type': 'string', 'description': 'The generation model (veo3, seedance, kling, etc.)'}, 'starting_grade': {'type': 'string', 'default': 'F', 'description': "The grade you're starting from â\x80\x94 'F', 'D', or 'C' (default 'F')"}}, 'additionalProperties': False}
Output schema 
{'type': 'object', 'additionalProperties': True}
enhance_prompt
Get a rewrite brief for this prompt + generator. YOU write the enhanced prompt from the brief. Returns a structured brief with score_before, rewrite_brief, and llm_instructions. category (optional): the ad vertical (e.g. "wellness", "beauty") if known. When set and conversion priors exist for it, the brief upgrades from craft advice to a conversion-justified one, backed by real ad-performance data. IMPORTANT: After you write the enhanced prompt, you MUST call track_enhancement(original_prompt, your_enhanced_prompt, generator) immediately. This is not optional — it records the improvement and is required for the graph to learn.
Read only
Input schema 
{'type': 'object', 'required': ['prompt', 'generator'], 'properties': {'prompt': {'type': 'string'}, 'category': {'type': 'string', 'default': ''}, 'generator': {'type': 'string'}}, 'additionalProperties': False}
Output schema 
{'type': 'object', 'additionalProperties': True}
list_generators
List all supported generation targets (providers + models) with medium and core strength.
Read only
Input schema 
{'type': 'object', 'properties': {}, 'additionalProperties': False}
Output schema 
{'type': 'object', 'additionalProperties': True}
my_story
Your Dali creative report — scoring history, generator stats, recent scorers, creative DNA.
Read only
Input schema 
{'type': 'object', 'properties': {}, 'additionalProperties': False}
Output schema 
{'type': 'object', 'additionalProperties': True}
prompt_neighbors
Find community A/B-grade prompts structurally similar to yours. Uses graph traversal (Memgraph) to locate prompts that share the most creative patterns with your input and scored A or B on the same generator. Returns what those prompts did right — so you can adopt the same moves. Use this when: - Your prompt scored C or below and you want inspiration - You want to see how the community solved the same creative problem - You need concrete A-grade examples, not abstract advice
Read only
Input schema 
{'type': 'object', 'required': ['prompt', 'generator'], 'properties': {'prompt': {'type': 'string', 'description': 'The prompt to find neighbors for.'}, 'generator': {'type': 'string', 'description': 'The generation model (veo3, midjourney, flux, etc.)'}}, 'additionalProperties': False}
Output schema 
{'type': 'object', 'additionalProperties': True}
score_creative
Score an actual ad IMAGE (not the text prompt) for conversion — before you spend. Conversion lives in the pixels, so this scores the real creative and gives you ONE answer combining two views, in a single call: • HEADLINE score = how much it visually resembles PROVEN WINNERS (Vertex embedding vs the live winner corpus). The sharpest predictor — it reads the whole look and self-solves archetype (a premium ad resembles premium winners, not scammy direct-response ones). • WHAT TO CHANGE = the specific winning attributes it's missing (Gemini vision vs category priors) — the actionable detail. • DEFECT GATE = generation defects (extra fingers, garbled text, warped anatomy). Use it on a generated image, a mockup, or any ad you're about to run. Returns: score — 0-100 headline: visual similarity to proven winners verdict — one-line looks-like-a-winner / partial / rework call looks_like — the real proven winners it resembles (advertiser, category, days-run) what_to_change — high-lift winning attributes it lacks, each with a fix sentence you_already_have — winning attributes it already has has_defect/defects — generation defects to fix before shipping detail — raw numbers {embedding_score, attribute_score} for transparency category examples: beauty, supplements, wellness, fitness, food, apparel, tech, pets. Leave category empty for a cross-vertical look-alike match + defect QA.
Read only
Input schema 
{'type': 'object', 'required': ['image_url'], 'properties': {'category': {'type': 'string', 'default': ''}, 'image_url': {'type': 'string'}}, 'additionalProperties': False}
Output schema 
{'type': 'object', 'additionalProperties': True}
score_creative_from_view
Score an ad creative YOU are looking at (e.g. a pasted/attached image) against the winning corpus — no URL needed. Use this when the user shares an image in the conversation: read the creative yourself and fill in what you see, and Dali scores it against what wins in the category (3,800+ proven winners), returning the conversion verdict and exactly which winning attributes it's missing. You (the model) provide the visual read; Dali provides the winning-data scoring. (For a fetchable image URL, prefer score_creative — it adds the embedding similarity headline, which needs the real pixels.) Fill these from looking at the image: category — vertical: beauty, wellness, supplements, fitness, food, apparel, tech, pets lighting — warm lighting | natural light | studio light | dramatic lighting | clinical bright | dark moody | neon subject — single person | group | product only | no person | before after subject_age — young adult | middle age | senior | child | none format — ugc selfie | testimonial | product hero | lifestyle | chart infographic | text meme | comparison text_density — none | light | heavy dominant_emotion — calm | excited | trust | fear | aspiration | neutral eye_contact — true if a person looks at camera offer_visible — true if a price/discount/offer is shown defects — list any generation defects (extra fingers, garbled text, warped anatomy); [] if clean Returns: conversion_score (0-100), verdict, matched (winning attributes it has), missing (high-lift attributes to add, each with a fix sentence), has_defect/defects.
Read only
Input schema 
{'type': 'object', 'required': ['category'], 'properties': {'format': {'type': 'string', 'default': ''}, 'defects': {'anyOf': [{'type': 'array', 'items': {'type': 'string'}}, {'type': 'null'}], 'default': None}, 'subject': {'type': 'string', 'default': ''}, 'category': {'type': 'string'}, 'lighting': {'type': 'string', 'default': ''}, 'eye_contact': {'type': 'boolean', 'default': False}, 'subject_age': {'type': 'string', 'default': ''}, 'text_density': {'type': 'string', 'default': ''}, 'offer_visible': {'type': 'boolean', 'default': False}, 'dominant_emotion': {'type': 'string', 'default': ''}}, 'additionalProperties': False}
Output schema 
{'type': 'object', 'additionalProperties': True}
score_prompt
Score a prompt for a generation target (0–100) and, if it's weak, return the rewrite brief — in ONE call. Reads intent with a fast heuristic keyword analyzer, scores the prompt, then: • score ≥ 70 (A/B) → returns the scorecard and tells you to proceed. • score < 70 (C/D/F) → returns the scorecard PLUS a rewrite brief so you can fix it without a second call. Write the enhanced prompt from the brief, then call track_enhancement(original, enhanced, generator). Returns a ScoreCard (overall, grade A–F, per-dimension breakdown, what's missing, anti-patterns, verdict) plus needs_enhancement, and enhancement_brief when weak. category (optional): the ad vertical (e.g. "wellness", "beauty") — when set and conversion priors exist, the brief upgrades to a conversion-justified rewrite. Supported generators: veo3, higgsfield, midjourney, flux, kling, sora, imagen…
Read only
Input schema 
{'type': 'object', 'required': ['prompt', 'generator'], 'properties': {'prompt': {'type': 'string'}, 'category': {'type': 'string', 'default': ''}, 'generator': {'type': 'string'}}, 'additionalProperties': False}
score_variations
Score 2–8 prompt variations for the same generator and rank them best-to-worst. Use this when you've drafted multiple versions of a prompt and want to pick the winner without burning generation credits. Returns a ranked list with per-dimension comparison so you can see exactly why one variant beats another.
Read only
Input schema 
{'type': 'object', 'required': ['prompts', 'generator'], 'properties': {'prompts': {'type': 'array', 'items': {'type': 'string'}, 'description': 'List of 2â\x80\x938 prompt variants (same creative intent, different wording)'}, 'generator': {'type': 'string', 'description': 'Target generator for all variants'}}, 'additionalProperties': False}
Output schema 
{'type': 'object', 'additionalProperties': True}
suggest_generator
Recommend the best generator for your creative concept and per-generation budget. Analyzes the concept's creative signals (motion, style, subject type, use case) and matches them to generators within your budget. Returns a ranked list so you can make an informed choice before scoring the actual prompt.
Read only
Input schema 
{'type': 'object', 'required': ['concept'], 'properties': {'concept': {'type': 'string', 'description': 'What you want to make â\x80\x94 subject, style, mood, format, use case'}, 'budget_usd_max': {'type': 'number', 'default': 1.0, 'description': 'Max USD per generation attempt (default $1.00)'}}, 'additionalProperties': False}
Output schema 
{'type': 'object', 'additionalProperties': True}
track_enhancement
Record an enhancement pair in the Dali graph brain. Call this AFTER you write an enhanced prompt from score_prompt's brief or enhance_prompt. This records the before→after improvement so the graph learns which rewrites consistently push scores up — enriching creative_patterns and community_benchmark over time. Returns before/after scores so you can confirm the delta.
Read only
Input schema 
{'type': 'object', 'required': ['original_prompt', 'enhanced_prompt', 'generator'], 'properties': {'generator': {'type': 'string'}, 'enhanced_prompt': {'type': 'string'}, 'original_prompt': {'type': 'string'}}, 'additionalProperties': False}
Output schema 
{'type': 'object', 'additionalProperties': True}
History

Recent tool changes

Added
analyze_winning_formula
Sept. 17, 2026, 12:43 p.m.
Added
score_creative_from_view
Sept. 17, 2026, 12:43 p.m.
Added
score_creative
Sept. 17, 2026, 12:43 p.m.
Added
list_generators
Sept. 17, 2026, 12:43 p.m.
Added
dali_version
Sept. 17, 2026, 12:43 p.m.
Added
enhancement_path
Sept. 17, 2026, 12:43 p.m.
Added
prompt_neighbors
Sept. 17, 2026, 12:43 p.m.
Added
my_story
Sept. 17, 2026, 12:43 p.m.
Added
community_benchmark
Sept. 17, 2026, 12:43 p.m.
Added
creative_patterns
Sept. 17, 2026, 12:43 p.m.
Added
score_variations
Sept. 17, 2026, 12:43 p.m.
Added
suggest_generator
Sept. 17, 2026, 12:43 p.m.
Added
track_enhancement
Sept. 17, 2026, 12:43 p.m.
Added
enhance_prompt
Sept. 17, 2026, 12:43 p.m.
Added
score_prompt
Sept. 17, 2026, 12:43 p.m.
Added
analyze_intent
Sept. 17, 2026, 12:43 p.m.
Discover

Similar MCP servers

ai-content-drop

com.aicontentdrop/ai-content-drop

Generates AI images, videos, UGC clips, avatars, and finished ads, while organizing creative assets and campaign boards.

Siren

ai.mysiren/siren

Plans, renders, and posts on-brand visual marketing campaigns.

Picorn

io.github.cueqzapper/picorn

Creates and edits layered social images, videos, slideshows, vector assets, and marketing projects with persistent editable canva…

Create Web Page

com.create-web-page/create-web-page

Creates, edits, previews, publishes, and manages hosted link-in-bio and landing pages with configurable content blocks, themes, m…

Postclick by PPC.io: Landing Page CRO

io.ppc/postclick-landing-page-cro

Audits landing pages, analyzes buyers and objections, generates copy and design concepts, builds HTML pages, and exports or share…

MagicScreenshots

io.github.Humanleap/magicscreenshots-mcp

Searches App Store screenshot references and preview videos, and supports screenshot restyling and localization jobs.

WebZum - The Hosting Layer for AI-Generated Web Content

io.github.suprraz/webzum

Creates, edits, clones, and hosts live HTML/CSS/JS websites, including SEO-focused business and lead-generation pages.

uxgen

ai.uxgen/ecommerce-conversion

Audits and assembles ecommerce pages, generates product imagery and packshots, supports Shopify sections, and provides SEO and co…