AEGOV DLS (UAE Design System)
UAE Design System (AEGOV DLS) for AI assistants: component catalogue, design tokens, UAE PASS & Emirates ID scaffolds, snippet validation.
README
DLSForge — UAE Design System (AEGOV DLS) tooling
Community project. Not affiliated with or endorsed by TDRA.
npm-workspaces monorepo holding the public, MIT-licensed DLSForge packages:
| Package | What it is | Status |
|---|---|---|
@dlsforge/aegov-rules-core |
Machine-readable model of the AEGOV DLS: component schemas, resolved design tokens, catalogue loader, and the DLS rule engine shared by every DLSForge tool. | published: 0.1.0 on npm |
@dlsforge/aegov-mcp |
MCP server exposing the core to AI coding assistants — listComponents, getComponent, getTokens, scaffoldUaePass, scaffoldEmiratesId, validate_snippet. |
published: 0.1.0 on npm (0.1.1 shared-core release deferred) |
@dlsforge/aegov-audit (Mizan) |
Compliance & accessibility auditor for UAE government sites (axe-core + Lighthouse + DLS rules over the rendered DOM), consuming the same core. Ships a CLI and a reusable GitHub Action. | published: 0.0.1 on npm |
The two tools mirror each other: the MCP server generates on-standard government UI, Mizan audits it — both enforcing the same rules from the shared core, so the standard is defined once.
The generate → verify loop
@dlsforge/aegov-rules-core ← the standard, defined once (catalogue + rule engine)
│
├── @dlsforge/aegov-mcp → assistants GENERATE valid government UI
└── @dlsforge/aegov-audit → Mizan VERIFIES a finished/in-progress site
Working in this repo
npm install # once, at the root — links the workspaces
npm run build # builds rules-core → mcp → audit (order matters)
npm test # all suites, every package
npm run evals # the 10 government-screen evals (mcp)
npm run evals:audit # Mizan's fixture-site evals (audit)
npm run smoke # stdio smoke test (mcp)
npm run validate # catalogue lint + invariants (rules-core)
Mizan's suites render pages, so npx playwright install chromium is needed once for npm test / npm run evals:audit.
See CLAUDE.md for the hard rules, STAGE1-HANDOFF.md / STAGE2-HANDOFF.md for the build briefs, and each package's own README for usage.
License
MIT — see LICENSE.
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
Neon Database
MCP server for interacting with Neon Management API and databases
E2B
Using MCP to run code via e2b.
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.