Visily MCP

by visily-app

Not rated
GitHub

About

Turn UI designs into responsive applications with Visily MCP

Details

Author
visily-app
Categories
Design, Other, AI, Developer Tools

Setup

Install Visily MCP in your MCP client (Claude Desktop, Cursor, Windsurf, and others).

Repository: https://github.com/visily-app/mcp-plugins

Follow the installation instructions in the repository README, then restart your MCP client.

Visily is an AI design canvas that turns text prompts, screenshots, URLs & more into UI designs that are as easy to edit as a Google Slide. The Visily MCP server brings those designs into your AI coding agent: point it at a Visily board or screen and your agent can find it, turn it into application code, or pull its theme tokens.

[!NOTE]Access requirement.The Visily MCP works only on workspaces on aPro or Businessplan where you are the workspace creator or have aneditorlicense. Free workspaces and viewer/guest roles are not supported. This is enforced on every request.

Each platform's drop-in files live underplugins/<platform>/.

claude plugin marketplace add visily-app/mcp-plugins claude plugin install visily@visily

Then reload Claude Code and run/mcp→ selectvisily→ complete the OAuth sign-in. Full walkthrough:installation-guides/claude.md.

Cursor 2.5+ packaged plugin — install from a local clone in the agent chat:

Reload Cursor; the MCP server appears underSettings → MCP(OAuth on first use) and the Visily skill loads automatically. Details:plugins/cursor/README.md.

Cline can connect directly to the hosted Visily MCP server with Streamable HTTP:

{ "mcpServers": { "visily": { "type": "streamableHttp", "url": "https://app.visily.ai/api/mcp" } } }

Full agent-readable install guidance:llms-install.md.

codex plugin marketplace add visily-app/mcp-plugins codex plugin add visily@visily

Authorize via OAuth on first use. Full walkthrough:installation-guides/codex.md.

ChatGPT connects to remote MCP servers viaDeveloper Modecustom connectors (Plus, Pro, Business, or Enterprise). EnableSettings → Connectors → Advanced → Developer mode, add a custom connector pointing at the server URL above, and complete OAuth. Then pasteplugins/chatgpt/AGENTS.mdinto a Project/GPT's instructions. Steps:plugins/chatgpt/SETUP.md.

Copyplugins/antigravity/.agents/into your project root and mergeplugins/antigravity/mcp_config.jsoninto your global MCP config. Details:installation-guides/antigravity.md.

Copyplugins/kiro/into your Kiro powers directory (it containsPOWER.md, per-intentsteering/workflows, andmcp.json). Mergemcp.jsoninto your Kiro MCP config and authorize via OAuth. The Power activates on Visily URLs and find/build/theme intents.

Install the hosted Visily MCP server with a one-click Replit install link:installation-guides/replit.md.

Commitplugins/lovable/AGENTS.mdto your repo root and add the Visily MCP connector in the Lovable UI. Details:plugins/lovable/SETUP.md.

v0supports custom MCP servers natively. Add the server URL above viaSettings → MCP Connections(orAdd MCPin the prompt form) and authorize via OAuth, then commitplugins/v0/AGENTS.mdto your repo root. Details:plugins/v0/SETUP.md.

Any client that supports Streamable-HTTP MCP can connect with this config:

{ "mcpServers": { "visily": { "url": "https://app.visily.ai/api/mcp" } } }

This covers VS Code (Copilot), Windsurf, Cline, Gemini CLI, and similar tools. Check your client's docs for where MCP server config lives; OAuth runs on first use.

[!NOTE]Google AI Studiodoes not natively support MCP connectors yet (it only works through third-party browser bridges, which we don't recommend). For a Google-native option, useFirebase Studio, which supports MCP servers via.idx/mcp.json— drop the sameurlconfig there. We'll add a first-class recipe when AI Studio ships native MCP support.

Give the agent a Visily link and a clear intent. The agent extracts the IDs from the URL — it doesn't open the page.

- "Find the Visily board I was working on for the 4.6 release and give me the link."
- "Build this Visily screen as React + Tailwind:https://app.visily.ai/projects/abc/boards/456/elements/789"
- "Implement this board in Next.js, reusing mysrc/components/uicomponents."
- "Apply my Visily board theme to this app'sglobals.css."

https://app.visily.ai/projects/{projectId}/boards/{boardId}/elements/{elementId}

Structure your Visily file for better code

The more intent your design carries, the better the generated code:

- Name your screens and key groups semanticallyin Visily — names flow into the export and into the link-matching for "find my board."
- Lean on Visily's theme / design systemso the agent can apply real tokens instead of guessing colors and radii.
- Ask for one screen at a timefor large boards — smaller selections produce more reliable results.

The server also shipsprompts(e.g.find_visily_board,generate_code_from_element,apply_board_theme) andresources(visily://docs/...) that your agent reads on demand.

Set project-level guidance so output stays consistent — like onboarding notes for a new teammate.

Cursor(.cursor/rules/visily-quality.mdc):

--- description: Visily code-generation rules alwaysApply: false --- - Treat Visily designData as a reference, not final code — rebuild semantically. - Apply the Visily theme tokens; never hardcode hex, radii, or spacing. - Reuse existing components in src/components/ui instead of duplicating. - Verify against get_screenshot for 1:1 layout before finishing.
## Visily MCP rules - Treat Visily designData as a reference, not final code — rebuild semantically. - Apply the Visily theme tokens; never hardcode hex, radii, or spacing. - Reuse existing components instead of duplicating; verify with get_screenshot.

plugins/is generated from a single shared source (shared/) byscripts/build.mjs. To change the integration, editshared/and runnpm run build— never editplugins/by hand. SeeCONTRIBUTING.md.

Enables AI assistants to interact with and automate Figma designs programmatically.

Figma MCP server for accessing Figma files, projects, comments, components, and design metadata from Claude, Cursor, and other AI agents.

Enables AI assistants to interact with Figma via WebSocket for reading data and design analysis.

Let your agents generate wireframes for your next app or feature, make iterations, and build off approved designs.

Build better interfaces with TypeUI design systems, UI prompts, and layout variations.

A platform for building design systems. This MCP server lets you create, manage and read your own design system with AI: build and edit design tokens, themes, components, and icons. Zaklad turns them into a Figma library and production-ready code.

Make your AI agent speak every language on the planet, using Lingo.dev Localization Engine.

AI-powered no-code app builder with 17 MCP tools — create projects, generate pages from natural language, AI text/image generation (GPT, Claude, Gemini, 14+ models), page CRUD, workflow execution, publish & version control. SSE transport, API key auth.

An MCP server that allows AI assistants to interact with Adobe After Effects.

No reviews yet — be the first

Sign in to leave a review

Use Google, GitHub, or an email account so ratings stay tied to real people.

Email sign in

No reviews posted yet.