mcpField
U
ui-mcp

ui-mcp

Local
github.com/Forge-SpaceDeveloper Tools2Updated 27w ago

About ui-mcp

ui-mcp is an MCP server for generating UI and backend code, intended for developers working across five frameworks. Its 22 tools cover code creation, design analysis, Figma workflows, and accessibility auditing, with optional brand identity context.

Key features

  1. 01Scaffold full applications and backend projects
  2. 02Generate components, forms, pages, and prototypes
  3. 03Create API routes and backend modules
  4. 04Parse Figma context and push design variables
  5. 05Audit accessibility and analyze design references

Use cases

  1. 01Build a project scaffold for a selected framework
  2. 02Turn a screenshot or wireframe into a component
  3. 03Apply brand tokens to generated UI
  4. 04Review interfaces for accessibility issues

MCP support

Exposes 22 tools and MCP resources through a server that can be run with npx, installed globally, or run in Docker. It accepts an optional brand_identity parameter and requires FIGMA_ACCESS_TOKEN only for Figma tools.

Configuration

Local server config is the same for every client. Copy it into your client’s MCP config file.

mcp.json · Universal config
{
"mcpServers": {
"forge-space-ui": {
"command": "npx",
"args": [
"-y",
"@forgespace/ui-mcp"
]
}
}
}
Run commandnpx -y @forgespace/ui-mcp

Local servers need a runtime on your machine (e.g. Node.js 18+). Config file locations differ by client; see your client’s docs.

Packages
npm@forgespace/ui-mcp0.25.0

Tools

38

Saved tool list · updated 2w ago

ParameterTypeRequiredDescription
moodenumNoDesign mood/personality for composed pagesbold | calm | playful | professional | premium | energetic | minimal | editorial | futuristic | warm | corporate | creative
stylingenumNoStyling frameworktailwindcss
industryenumNoTarget industry for composed pagessaas | fintech | ecommerce | healthcare | education | startup | agency | media | devtools | general
frameworkenumYesFrontend framework to scaffoldreact | nextjs | vue | angular | html | svelte
architectureenumNoProject architecture patternflat | feature-based | atomic
project_namestringYesProject name (used for directory and package.json)
visual_styleenumNoVisual style for composed pagesglassmorphism | neubrutalism | soft-depth | bento-grid | gradient-mesh | dark-premium | minimal-editorial | linear-modern | retro-playful | corporate-trust
brand_identitystringNoJSON string from branding-mcp generate_brand_identity. Overrides design context with brand tokens.
state_managementenumNoState management solutionuseState | zustand | pinia | signals | none

Details

From the project README
Forge Space

@forgespace/ui-mcp

AI-driven UI and backend code generation via Model Context Protocol. 22 tools, 5 frameworks, brand-aware, npm-published, and MCP Registry-ready.

npm version CI Coverage License: MIT TypeScript MCP Node.js

Part of the Forge Space ecosystem.

Siza Capabilities

Architecture

@forgespace/ui-mcp is a thin protocol adapter. All AI/generation logic lives in @forgespace/siza-gen:

@forgespace/ui-mcp (~355 KB)       @forgespace/siza-gen (~1.8 MB)
├── src/index.ts (MCP server)      ├── ml/        (embeddings, quality, training)
├── tools/     (22 tool defs)      ├── generators/ (react, vue, angular, svelte, html)
├── services/  (figma, analysis)   ├── registry/   (502 snippets, compositions, packs)
├── resources/ (MCP resources)     ├── feedback/   (self-learning, pattern promotion)
└── lib/       (browser, image)    └── quality/    (anti-generic rules, diversity)

Quick Start

# NPX (instant)
npx -y @forgespace/ui-mcp@latest

# Global install
npm install -g @forgespace/ui-mcp && forgespace-ui-mcp

# Docker
docker build -t forgespace-ui-mcp . && docker run --rm -i forgespace-ui-mcp
IDE Integration

Add to your MCP configuration (Claude Code, Windsurf, Cursor, VS Code):

{
  "mcpServers": {
    "forgespace-ui-mcp": {
      "command": "npx",
      "args": ["-y", "@forgespace/ui-mcp@latest"],
      "env": {
        "FIGMA_ACCESS_TOKEN": "your_token_here"
      }
    }
  }
}

Tools

ToolCategoryDescription
scaffold_full_applicationCodeFull project boilerplate (React/Next.js/Vue/Angular/HTML + Tailwind)
generate_ui_componentCodeUI components with style audit, supports shadcn/ui, Radix, Headless UI, Material, PrimeVue
generate_formCodeProduction forms with Zod/Yup validation, multi-step flows, accessible markup
generate_page_templateCodePre-built pages (landing, dashboard, auth, pricing, CRUD)
generate_prototypeDesignInteractive HTML prototypes with navigation
generate_design_imageDesignSVG/PNG mockups of UI screens
image_to_componentCodeScreenshot/wireframe to framework-specific component
refine_componentCodeImprove components via natural language feedback
generate_api_routeBackendAPI routes with validation, auth, and error handling
generate_backend_moduleBackendFull feature modules with routes, services, middleware
scaffold_backendBackendComplete backend projects with auth, DB, monitoring
generate_from_template_packCodeMulti-page apps from curated packs (SaaS, Landing, AI Chat)
figma_context_parserContextRead Figma files, extract tokens, map to Tailwind
figma_push_variablesDesignWrite design tokens back to Figma
fetch_design_inspirationContextExtract visual metadata from URLs
analyze_design_referencesContextAnalyze design references, detect patterns
analyze_design_imageMLAnalyze design images for training data
analyze_component_libraryContextAnalyze component library patterns
audit_accessibilityQualityWCAG 2.1 audit with fix suggestions
submit_feedbackQualitySubmit feedback to improve future output
payments_refundBackendRequest payment refund with Zod-validated params (payment_id, amount, reason, currency)
manage_trainingMLTraining data ingestion and fine-tuning

Framework & Library Support

LibraryReactVueAngularSvelteHTML
shadcn/uishadcn/uishadcn-vueTailwindbits-uiTailwind
Radix@radix-ui/react@radix-ui/vueTailwind@radix-ui/svelteTailwind
Headless UI@headlessui/react@headlessui/vueTailwind@headlessui/svelteTailwind
Material@mui/materialVuetify@angular/material@smui/materialTailwind
PrimeVueHeadless UIprimevueprimengTailwindTailwind
noneTailwind CSSTailwind CSSTailwind CSSTailwind CSSTailwind CSS

Brand Identity Integration

All generation tools accept an optional brand_identity parameter — a JSON string from branding-mcp's generate_brand_identity tool. When provided, brand colors, typography, and spacing are injected into the design context.

Environment Variables

VariableRequiredDescription
FIGMA_ACCESS_TOKENOnly for Figma toolsToken from Figma Settings
SENTRY_DSNOptionalSentry DSN for error reporting (uncaught exceptions and unhandled rejections)

Distribution

  • npm — published as @forgespace/ui-mcp
  • MCP Registry metadata — repository includes server.json and mcpName metadata for registry submission
  • Tag release automation — pushing v* runs npm publish with provenance, then publishes the same version to the MCP Registry via GitHub OIDC
  • Weekly registry ops — .github/workflows/mcp-registry-status.yml refreshes one issue with npm and MCP Registry drift, visibility, and next actions
  • GitHub — source, issues, releases, and Discussions live under Forge Space

Development

npm install && npm run build
npm test                  # 437 tests, 35 suites
npm run validate          # lint + format + typecheck + test

Community

GitHub Workflow

This repository follows the shared Forge Space GitHub work-management baseline:

  • Discussions for ideas, RFCs, Q&A, and announcements
  • Issues for actionable delivery work
  • Projects for roadmap visibility and cross-repo reporting

See Forge-Space/.github GOVERNANCE.md for the org-wide contract.

Scheduled monitoring runs that execute CodeQL require job-scoped security-events: write permission for SARIF upload.

The scheduled Security Monitoring workflow intentionally skips Codecov upload and relies on local coverage summary generation to reduce false alerting from third-party action download instability.

License

MIT

Comments

Markdown supported

New to MCP?

From what the protocol is to installing your first server, these answers cover most first questions.

An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.