$ show nuxt-ui-templates/docs
This repository provides a production-ready documentation template built on Nuxt 4, Nuxt UI 4, and Nuxt Content 3. The codebase implements a static site generator for technical documentation with full-text search, automatic navigation, dark mode, and optimized OG images. It includes a built-in MCP (Model Context Protocol) HTTP server that exposes two tools (`list-pages` and `get-page`) for AI assistants to discover and read documentation content programmatically. Additionally, it integrates `nuxt-llms` to pre-render `/llms.txt` and `/llms-full.txt` files for LLM consumption. The architecture follows a standard Nuxt/Nitro server-rendered app with prerendering enabled, relying on modules for search, image optimization, and content management. The repo is explicitly a template intended for forking, with clean configuration-driven customization via `app.config.ts` and a well-documented content structure.
The LLM identified 3 files worth highlighting for reuse:
Implements a Model Context Protocol tool that retrieves the full markdown content of a documentation page by path. Uses Zod for input validation, caches results via the `cache` option, and fetches raw content from the `/raw` server route. The tool includes detailed descriptions for AI assistant decision-making and robust error handling. This pattern demonstrates how to expose content store items as MCP tools in a Nuxt application.
Implements an MCP tool that lists all documentation pages with title, path, description, and URL. Queries the Nuxt Content collection server-side, caching results for one hour. The tool provides comprehensive usage guidance (when to use vs. when to use `get-page`) and returns structured JSON. This is an excellent example of creating an AI-optimized index for documentation content.
A Nitro server route that serves documentation pages as raw Markdown. It handles slug resolution, fetches the page from the content collection, injects title and description if missing, and uses `minimark` to stringify the body tree into Markdown with HTML formatting. This pattern provides a programmatic way to access content in its source format, useful for AI tools and external consumers.