A curated registry of Model Context Protocol servers, each with an automated security grade from our tool-surface scanner.
Context for the grades below — how inspection, tool poisoning, and the grade-vs-gate split work. Directory letters are Andrax scanner grades (mcpgrade-1.4.0), not Guard runtime scores.
Soft CTA: a grade finds risk on a snapshot; Guard enforces runtime controls on live MCP traffic (Free / Pro $49 / Team $399). Do not equate Andrax grades with Guard scores.
Run an MCP server? Paste its remote endpoint — we'll scan it (read-only) and publish a free, reproducible security grade. Genuine MCP servers get listed instantly.
Aggregates and summarizes Bulgarian news from leading outlets, with tools for semantic search, top stories, article browsing, and full article retrieval.
Bulk Meta ad campaign automation with Drive folder integration and spend guardrails.
Pre-connect trust checks for AI agents and MCP servers using HVTracker's public trust registry.
Experimental sandbox: custom-manufacturing quotes, lead time, DFM. Not a real supplier.