Dali by Lulu
PYPI · DALI-MCP · 2 COMPONENTS
The prediction MCP — score your prompt before you generate, so you never waste a credit.
Available components
Last scanned (1 hour ago)
Scores higher than 95% of PyPI servers
Category Design and Media
Recent critical change
GHSA-6q48-6c7w-9gw2 affects this package (21 Oct 2026). See the changelog before you install this server.
How this component scores in each security and reliability category. Every signal is checked automatically from public evidence about the published package, including repeated runs of it in an isolated sandbox, and we only credit what we can confirm. How we score → Why this is hard to score →
Supply Chain Security100
- No malware found by supply-chain analysis.Pass
- No known CVEs affecting this package version or its production dependencies.Pass
- Runs hatchling.build at install time, a recognised build step with no custom scripting around it. View diagnostics → Pass
- 1 of 22 dependencies flagged as unhealthy. View diagnostics → Partial
Provenance & Transparency97
- Source repository is publicly reachable at the declared URL. View diagnostics → Pass
- Cryptographically verified build provenance (signed, bound to Lulu-The-Narwhal/dali-mcp). View diagnostics → Pass
- Clear OSI-approved license (MIT).Pass
- Actively maintained (last published 114 days ago).Pass
- Disclosure check failed: no security disclosure policy was found in the source repository. See how to fix → Fail
Schema Quality & AI Usability83
- 100% of prompts and resources have a non-trivial description (not blank, and not just the item's name).Pass
- AI-judged instruction clarity (excellent).Pass
- Context-footprint check failed: tool/resource definitions use about 1621 tokens (~124/item across 13 items; 12 tools + 1 resources), over budget; trim descriptions and params. See how to fix → Fail
- Usage-examples check failed: none of the tools include examples. See how to fix → Fail
Stability & Change Management70
- Stability observed for 21 of 30 days with no destabilising changes; credit accrues until the full window elapses.Partial
Tool Coverage100
- 100% of tools have a non-trivial description (not blank, and not just the tool's name).Pass
- 100% of tool parameters carry a description.Pass
- Structured output schemas are declared (100% of tools); any adoption earns full credit.Pass
Tool Safety100
- No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.Pass
- We read all 12 captured tool definition(s), and no name or description among them implies an irreversible operation.Pass
- An AI judge read all 14 captured unit(s) of tool text and found none that tries to manipulate the model reading it.Pass
Capabilities100
- Implements a current MCP spec version (2026-07-28).Pass
Every change we have recorded for this component, newest first. Security-relevant changes are always shown. ▲ marks a change for the better, ▼ a change for the worse; unmarked changes are neutral.
- 4 Nov 26 +1
No change was recorded against any check on this day. Stability & Change Management went from 63 to 67. That category is still filling its 30-day observation window: 19 days of observed history at the previous scan, 20 at this one. The score rises as the window fills, whether or not the server changes.
- 3 Nov 26 −5
- Stability: pass → 0.63 functional
- 2 Nov 26 +15
- Malware scan: unverified → pass ▲ security
- 1 Nov 26 −15
- Malware scan: pass → unverified ▼ security
- 28 Oct 26 0
- Stability: 0.97 → pass security
- 27 Oct 26 0
- Stability: pass → 0.97 functional
- 22 Oct 26 +96
- GHSA-6q48-6c7w-9gw2 no longer affects this package ▲ security
- Known CVEs: fail → pass ▲ security
- Score status: failed → scored ▲ functional
- 21 Oct 26 −96
- GHSA-6q48-6c7w-9gw2 affects this package: none ▼ critical
- Known CVEs: pass → fail ▼ critical
- Score status: scored → failed ▼ critical
Diagnostic detail from the automated scan of this channel: what the scanner observed at each step, so you can see exactly where a check passed or failed. It is informational only and never changes the trust score.
Captured 5 Nov 2026 · Analysed pypi/dali-mcp@0.6.1
Provenance Verified
A signed build attestation was found and verified, binding this exact artifact to the source repository it claims to come from.
| Result | Verified |
|---|---|
| Ecosystem | pypi |
| Reason | Verified |
| Discovered via | Registry attestation endpoint |
| Source repo | Lulu-The-Narwhal/dali-mcp |
| Certificate issuer | https://token.actions.githubusercontent.com |
| Certificate SAN | https://github.com/Lulu-The-Narwhal/dali-mcp/.github/workflows/publish.yml@refs/tags/v0.6.1 |
| Rekor log index | 2164012663 |
| Predicate type | PyPI publish attestation https://docs.pypi.org/attestations/publish/v1 |
| Subject digest | sha256:5a5fe705c9db5010b8f3ed45988043e549971353295c2e802ae409aa3e3c6652 |
Background: How many MCP packages publish verified provenance →
Install scripts 1 script
| Hook | Tier | Command |
|---|---|---|
| build_backend | allowlisted | hatchling.build |
Background: Why install scripts are a supply-chain risk →
Dependencies 22 packages
| Packages resolved | 22 |
|---|---|
| Stale | 1 |
| Tree resolution | Complete |
Background: SBOMs and build attestations, explained →
The tools this component advertises to a client, with an estimated token cost for each. Expand a tool to see its parameters and schema. The per-tool counts are indicative and are not scored directly; the schema's total context footprint is one signal in Schema Quality & AI Usability. A tool's description is untrusted text the model reads on every call, which is what makes this list a security surface and not just an inventory: how tool poisoning works →
analyze_intent Analyze Intent ~87
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.
| Name | Type | Req | Description |
|---|---|---|---|
| medium | string | – | "image", "video", or "auto" (default, auto-detected) |
| prompt | string | yes | Raw creative text (rough idea or full prompt — both work) |
Structured output declared, but exposes no named fields.
No examples provided.
community_benchmark Community Benchmark ~91
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
| Name | Type | Req | Description |
|---|---|---|---|
| model | string | yes | Target generation model |
| prompt | string | yes | Your prompt to benchmark |
Structured output declared, but exposes no named fields.
No examples provided.
creative_patterns Creative Patterns ~156
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).
| Name | Type | Req | Description |
|---|---|---|---|
| grade | string | – | Minimum grade filter — "A" (only A-grade), "B" (A+B), "C" (A+B+C) |
| model | string | yes | Target generation model (veo3, seedance, kling, runway, wan, minimax, higgsfield, flux, midjourney, ideogram, firefly) |
Structured output declared, but exposes no named fields.
No examples provided.
dali_version Dali Version ~46
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.
Input schema present but exposes no named parameters.
Structured output declared, but exposes no named fields.
No examples provided.
enhance_prompt Enhance Prompt ~133
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.
| Name | Type | Req | Description |
|---|---|---|---|
| model | string | yes | Target generation model (veo3, seedance, kling, runway, wan, minimax, higgsfield, sora, flux, midjourney, ideogram, firefly, imagen) |
| prompt | string | yes | The prompt to enhance |
Structured output declared, but exposes no named fields.
No examples provided.
list_models List Models ~22
List all supported generation models with medium, creator, and core strength.
Input schema present but exposes no named parameters.
Structured output declared, but exposes no named fields.
No examples provided.
my_story My Story ~103
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.
Input schema present but exposes no named parameters.
Structured output declared, but exposes no named fields.
No examples provided.
score_and_enhance Score And Enhance ~107
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.
| Name | Type | Req | Description |
|---|---|---|---|
| generator | string | yes | Target generation model (veo3, seedance, higgsfield, flux, midjourney, etc.) |
| prompt | string | yes | The prompt to score and enhance |
Structured output declared, but exposes no named fields.
No examples provided.
score_prompt Score Prompt ~162
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
| Name | Type | Req | Description |
|---|---|---|---|
| model | string | yes | Target generation model |
| prompt | string | yes | The prompt to score |
Structured output declared, but exposes no named fields.
No examples provided.
score_variations Score Variations ~91
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.
| Name | Type | Req | Description |
|---|---|---|---|
| generator | string | yes | Target generation model |
| prompts | array | yes | List of prompt strings to compare (2–10 recommended) |
Structured output declared, but exposes no named fields.
No examples provided.
suggest_generator Suggest Generator ~88
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.
| Name | Type | Req | Description |
|---|---|---|---|
| budget_usd_max | number | – | Max spend per generation in USD (default $1.00) |
| concept | string | yes | What you want to create (plain language or a prompt) |
Structured output declared, but exposes no named fields.
No examples provided.
track_enhancement Track Enhancement ~100
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.
| Name | Type | Req | Description |
|---|---|---|---|
| enhanced_prompt | string | yes | The version you actually improved |
| generator | string | yes | Target generation model |
| original_prompt | string | yes | The un-enhanced prompt |
Structured output declared, but exposes no named fields.
No examples provided.
How do I install the Dali by Lulu MCP server?
Dali by Lulu runs locally as a PyPI package, launched with uvx dali-mcp. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.
pypi · dali-mcp
claude mcp add lulu-the-narwhal-dali -- uvx dali-mcp
What is the Dali by Lulu MCP server?
Dali by Lulu is an MCP server listed in the public MCP registry as io.github.Lulu-The-Narwhal/dali. The prediction MCP, score your prompt before you generate, so you never waste a credit. This page covers its PyPI package (dali-mcp).
Is the Dali by Lulu MCP server safe to use?
Dali by Lulu scores 92 out of 100 on VerifyMCP. We found no known CVEs affecting it as of 5 November 2026. Its build provenance is signed and verified. That is a record of what we were able to check automatically, not an endorsement. The category breakdown on this page shows every signal behind the number, including the ones we could not confirm.
What tools does the Dali by Lulu MCP server expose?
Dali by Lulu exposes 12 tools: analyze_intent, score_prompt, enhance_prompt, creative_patterns, community_benchmark, and 7 more. Their descriptions and schemas cost roughly 1,186 tokens of context every time the server is loaded.
Is the Dali by Lulu MCP server still maintained?
Dali by Lulu is still listed as active in the MCP registry. We last reached this channel on 5 November 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.
What licence is the Dali by Lulu MCP server under?
Dali by Lulu declares the MIT licence, which is OSI-approved. That covers the source only, and says nothing about the cost of any service it calls.