# VisualSpec MCP : reliable text and layout for AI-generated graphics **URL:** \ **Category:** Built for Cursor\ **Tags:** mcp, image-gen\ **Created:** [September 10, 2026, 10:21am UTC](https://forum.cursor.com/t/visualspec-mcp-reliable-text-and-layout-for-ai-generated-graphics/171243 "2026-09-10T10:21:17Z")\ **Posts on this page:** 1\ **Page:** 1
**Author:** ![Utkarsh\_Singh](https://avatars.discourse-cdn.com/v4/letter/u/3d9bf3/32.png) [@Utkarsh\_Singh](https://forum.cursor.com/u/Utkarsh_Singh)\ **Post date:** [September 10, 2026, 10:21am UTC](https://forum.cursor.com/t/visualspec-mcp-reliable-text-and-layout-for-ai-generated-graphics/171243/1 "2026-09-10T10:21:17Z")
AI image models are great at generating visuals, but they still struggle with exact text, typography, and layout. I built **VisualSpec** , an open-source tool that separates these jobs: - AI generates the image/background - SVG/code renders the exact text and layout - Visual QA checks margins, dimensions, and layout issues - MCP lets Cursor use VisualSpec directly Demo 👇 ![demo](https://us1.discourse-cdn.com/cursor1/original/3X/7/c/7cda3b41b0543aca3812006faec2ab1a800f93d9.gif) Run it: `npx @utkarshx27/visualspec mcp` GitHub: > **[GitHub - utkarshx27/visualspec: Structured, constraint-aware visual generation and...](https://github.com/utkarshx27/visualspec)** > > Structured, constraint-aware visual generation and deterministic layout for AI agents npm: > **[@utkarshx27/visualspec](https://www.npmjs.com/package/@utkarshx27/visualspec)** > > Structured, constraint-aware visual generation and deterministic layout for AI agents. Latest version: 0.1.0, last published: 4 minutes ago. Start using @utkarshx27/visualspec in your project by running \`npm i @utkarshx27/visualspec\`. There are no... I’m looking for feedback from Cursor/MCP developers, and I’d also love contributors interested in TypeScript, AI image generation, templates, and visual QA. Would love to know what you think or what you would want VisualSpec to support next.