Open-Sourced MCP Servers Directory

Implements a centralized web-based directory (mcp.so) that aggregates MCP servers submitted by the community, organizing them by category and making them searchable through a Next.js frontend backed by Supabase. The system accepts both GitHub URLs and raw JSON metadata, parses project information through a dedicated parseProject() service function, and stores normalized data in a relational schema with projects and categories tables for efficient querying and filtering.

Processes submitted GitHub URLs or JSON payloads through a multi-stage extraction pipeline: parseProject() validates and normalizes input data, Jina AI extracts structured content from repository README and documentation, and OpenAI generates concise summaries and categorization. The enriched metadata is persisted to Supabase with fields for description, tags, installation instructions, and usage examples, enabling consistent presentation across the directory.

Implements the MCP Directory frontend using Next.js pages (Landing, Project Detail, Categories) and reusable React components (Search, Markdown Renderer, etc.), with responsive CSS for mobile, tablet, and desktop viewports. The architecture uses Next.js server-side rendering (SSR) or static generation (SSG) for performance and SEO, with client-side React components for interactive features like search and filtering. The UI layer communicates with backend API routes for data fetching and submission.

Implements data persistence using Supabase (PostgreSQL-based) with two primary tables: projects (storing MCP server metadata including name, description, repository URL, category, tags, installation instructions) and categories (defining the taxonomy for organizing servers). The schema includes proper indexing on frequently-queried fields (name, category, tags), foreign key relationships for referential integrity, and timestamp fields (created_at, updated_at) for tracking submission and modification times. The architecture supports full-text search through indexed text fields and enables efficient filtering and pagination.

Exposes Next.js API routes that accept POST requests with either a GitHub repository URL or raw JSON project metadata, validates input through a Project model with TypeScript type checking, and persists submissions to Supabase after enrichment. The API layer implements saveProject() to handle database writes, with support for both creation and updates, and includes error handling for invalid URLs, missing required fields, and API failures during enrichment.

Implements search functionality through Next.js API endpoints that query the Supabase projects table using full-text search on server names, descriptions, and tags, combined with faceted filtering by category, tags, and other metadata fields. The frontend React components (Search component) provide UI for query input and filter selection, with results ranked by relevance and paginated for performance. The system maintains a denormalized schema with indexed text fields to enable fast queries across thousands of server entries.

Implements sitemap management APIs that dynamically generate XML sitemaps listing all MCP server project pages, with automatic updates triggered when new servers are submitted or existing ones are modified. The system maintains a sitemap index that references individual sitemaps (split by project count for Google compliance), with proper lastmod timestamps and priority values. Sitemaps are served at standard locations (/sitemap.xml, /sitemap-index.xml) for search engine crawlers to discover and index all directory content.

Maintains a categories table in Supabase that defines the taxonomy for organizing MCP servers (e.g., 'Data Access', 'API Integration', 'Development Tools'), with support for hierarchical relationships and metadata like descriptions and icons. The system enforces referential integrity between projects and categories, allowing servers to be tagged with one or more categories. The frontend Categories page displays all available categories with server counts, enabling users to browse by functional area rather than keyword search.

Generates dynamic Next.js pages for each MCP server that display comprehensive project information including description, installation instructions, usage examples, and links to the source repository. The system renders markdown content (extracted from README files) using a Markdown Renderer component, with syntax highlighting for code blocks and proper formatting for nested lists and tables. Each project page includes metadata like creation date, last update, category, tags, and direct links to GitHub repository and installation documentation.

Implements i18n support through a pagejson/en.json configuration file that stores all user-facing text strings, enabling translation to additional languages without code changes. The system uses language-specific routing (e.g., /en, /fr) or locale detection to serve appropriate language variants. The architecture supports adding new languages by creating additional JSON files and updating the routing configuration, with fallback to English for missing translations.

Integrates analytics tracking (likely Google Analytics or similar) to monitor user behavior including page views, search queries, category browsing patterns, and project detail page visits. The system collects anonymized metrics on which servers are most popular, which search terms drive traffic, and which categories receive the most interest. This data informs decisions about featured servers, category organization, and directory improvements without collecting personally identifiable information.

Automatically generates Open Graph meta tags (og:title, og:description, og:image) for each project detail page, enabling rich previews when servers are shared on social media platforms like Twitter, LinkedIn, and Discord. The system includes project name, description, and optionally a generated or uploaded image in the metadata, with fallback to directory-level defaults for servers without custom images. This improves discoverability through social sharing and makes server links more visually appealing in social feeds.