VisualSpec MCP server
io.github.utkarshx27/visualspec·v0.1.0Structured, constraint-aware visual generation and deterministic layout for AI agents
0 stars38 downloads/wk
Reviews
Write oneNobody has reviewed VisualSpec yet.
If you have run it, two minutes of your experience saves the next person an afternoon.
VisualSpec tools (7, 2 write)
write = sends, deletes, buys or postsRead from the package source without running it. The installed server may list more.
visual_brief_to_specConvert a natural-language creative brief or user request into a structured VisualSpec specification
visual_check_qawrite actionRun automated visual QA checks (safe margins, max lines, exact copy, slot compliance, output dimensions)
visual_generatewrite actionRun the full visual generation pipeline (model adapter + deterministic typography overlay + QA)
visual_list_resourcesList all available platform packs (Instagram, LinkedIn, etc.) and structural templates (Product Launch, Quote Card, Stat Card)
visual_renderRender deterministic typography, layout, and styling to a PNG asset without requiring an AI image API key
visual_repairDiagnose QA failures and automatically formulate & apply localized repairs without full regeneration
visual_validate_specValidate a VisualSpec YAML or JSON against the schema
Public scan report
scanner v0.1.10 · 2026-10-02 · same rubric, same numbers if you re-run it
- Code scan79 source files scanned25/25
- –Live reliabilityno gateway calls yet and no remote to proben/a
- –Tool poisoningtools not inspected (local package is not executed); not countedn/a
- Auth qualitystatic API keys via environment variables6/15
- Maintenancelast push 22 days ago15/15
- Maintainer identityregistry namespace matches repository owner; GitHub account older than a year8/10
How VisualSpec compares
Against every graded MCP server, from our own scans and uptime checks. Updated after each scan run.
- Safety score
- 83/100
- higher than 65% of 48,243 servers
- Tools
- 7
- the typical server has 7
- Tools that change things
- 29%
- typical: 0%. Fewer write tools means less an agent can break
- Downloads a week
- 38
- more than 28% of 12,306 servers with a package
What its tools let an agent do: 5 read · 2 change
Install VisualSpec in Claude Code, Cursor or VS Code
Runs npx -y @utkarshx27/visualspec on your machine. Read the scan report first; the gateway never runs local packages.
claude mcp add visualspec -- npx -y @utkarshx27/visualspec
What the publisher says
From the VisualSpec repository's README, as published. We do not edit it. Read it on GitHub
VisualSpec
Deterministic visual generation for AI agents.
AI creates the imagery. VisualSpec guarantees the typography and layout.
# Instant workspace setup (no clone required)
npx @utkarshx27/visualspec init
# Launch local MCP Server for Cursor, Claude Desktop, or Antigravity
npx @utkarshx27/visualspec mcpThe Core Problem
Most image-generation workflows fail for social and marketing graphics because a single natural-language prompt is expected to handle too many concerns at once:
- subject & background
- exact typography & wording
- platform dimensions & safe margins
- visual hierarchy & negative space
- brand color rules & constraints
Image models frequently hallucinate gibberish text, truncate words, or disregard composition rules.
The Solution: Layer Separation
VisualSpec separates generative concerns from deterministic concerns:
- Generative Layers (AI Models): Photography, 3D subjects, atmospheric backgrounds, textures, lighting.
- Deterministic Layers (Code & SVG Engine): Exact headlines, subtitles, badges, logos, metrics, safe margins, and layout rules.
- Structured Visual Spec: A machine-readable YAML specification that acts as the single contract.
- Visual QA & Targeted Repair: Verifies geometry, margins, and exact copy invariants, synthesizing localized repairs without regenerating entire scenes.
User Brief / Intent
│
▼
Visual Spec (spec.yaml)
│
┌───┴──────────────┐
▼ ▼
Platform Pack Template Pack
│ │
└───┬──────────────┘
▼
Spec Resolver
│
┌───┴───────────────────────┐
▼ ▼
Model Adapter Deterministic Layout
(Generative Base) (SVG Typography / Overlay)
│ │
└───┬───────────────────────┘
▼
Compositor (Sharp)
│
▼
Visual QA (Constraints, Safe Margins, Exact Copy)
│
├── PASS ──► Final Asset Bundle
│
└── FAIL ──► Targeted Repair PlannerDocumentation
- Architecture & Design Principles
- VisualSpec Schema & Contract
- MCP Server Setup (Cursor, Claude, Antigravity)
- Adding a New Image Model Provider
- Contributing Guidelines
Quickstart
Instant Run (No Install Required)
# Initialize a new VisualSpec workspace
npx @utkarshx27/visualspec init
# Launch local MCP Server for Cursor, Claude, or Antigravity IDE
npx @utkarshx27/visualspec mcpOr Install Globally
npm install -g @utkarshx27/visualspec
# Use CLI commands directly
visual init
visual mcpOr Build from Source
git clone https://github.com/utkarshx27/visualspec.git
cd visualspec
npm install
npm run build1. Initialize a Project
npx @utkarshx27/visualspec init2. Validate a Visual Spec
npx @utkarshx27/visualspec validate examples/product-launch/spec.yaml3. Inspect the Compiled Generation Prompt
Shortened. The full README is on GitHub.
Nothing above is checked by us. What we check is on the safety report.
VisualSpec: common questions
- Is VisualSpec MCP server safe?
- Mostly: it is graded B (83/100). Read the VisualSpec safety report
- How do I install VisualSpec?
- It runs on your machine. Copy the Claude Code, Cursor, VS Code or Claude Desktop config from the install section.
- Does VisualSpec need an API key?
- Yes. The registry entry asks for
OPENAI_API_KEY,GEMINI_API_KEY. - Is VisualSpec maintained?
- The last commit was 56 days ago (2026-09-10). The latest release is v0.1.0.
- How does VisualSpec compare with other MCP servers?
- safety score 83/100 (higher than 65% of 48,243 servers); tools 7 (the typical server has 7); tools that change things 29% (typical: 0%. Fewer write tools means less an agent can break). Full comparison.