by thorsten · MCP Server · ★ 623
Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h
Flagged: privileged Docker. Scanned against 42 published rules built on the SlowMist agent-security taxonomy, refreshed every 8 hours. Full audit →
The quality score combines nine heuristic checks of the repo and its README: completeness, clarity, specificity, examples, structure, agent readiness, step-by-step content, instruction quality and security notes. It rates how well the project explains itself to an agent, not the code.
| Stars | 623 |
| Forks | 268 |
| Language | PHP |
| Category | MCP Server |
| License | MPL-2.0 |
| Quality Score | 63/100 |
| Open Issues | 10 |
| Last Updated | 2026-11-07 |
| Created | 2009-08-04 |
| Platforms | browser, docker, k8s, mcp |
| Est. Tokens | ~18k |
phpMyFAQ What is phpMyFAQ? phpMyFAQ is a multilingual, AI-ready, and scalable FAQ platform built for modern knowledge management. Powered by PHP 8.4+ and a fully database-driven architecture, it delivers fast search with Elasticsearch/OpenSearch, flexible multi-user permissions, and a powerful content management system with revision history and WYSIWYG editing.
Looking for a phpMyFAQ alternative? If you're comparing phpMyFAQ with other mcp server tools, these 6 projects are the closest alternatives on Agent Skills Hub — ranked by topic overlap, star count, and community traction.
Faucet is an open-source, single-binary server that turns any SQL database into a secure, governed REST API wi
ServBay is an AI-native local development tool. It gives your AI agents a real dev environment so that your AI
🦭 Run and operate MariaDB in a cloud native way
EnvKit — free local development environment for Windows & macOS: nginx/Apache, multiple PHP versions, MySQL/Ma
Fulling is an AI-powered Full-stack Engineer Agent. Built with Next.js, Claude, shadcn/ui, and PostgreSQL. Use
One SQL interface for 60+ tools (e.g., GitHub, Notion, Airtable). Plug into any LLM through MCP.
Explore other popular mcp server tools:
Grades come from a rule-based scan built on the SlowMist agent-security taxonomy: 42 published rules, covering credential harvesting, data exfiltration, curl | sh installers and more. It is a first-layer scan, not a manual audit — we say so rather than overstate it.
The scale of the problem is documented independently: Liu et al. (2026), in a study of 31,132 agent skills, report that 26.1% contain security vulnerabilities. Our own full-catalog census is published as a citable open dataset.
Sources & who's responsible: