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 allow/deny/audit on live MCP traffic (mcpgrade-2.0.0). Do not equate the two scores.
Persistent project context for Claude Desktop and Claude Code, built on the IANA-registered .faf format.
Persistent project context for xAI Grok using the IANA-registered .faf format, shared across AI sessions.
Persistent project context for xAI Grok using the IANA-registered .faf format, shared across AI sessions.
Sync project context once and distribute it to all IDE-specific formats including Cursor, Windsurf, VS Code, and Cline.
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.