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.
Diagnose common dog behaviour problems, get program pricing, and submit the free assessment.
Public read-only MCP server providing AI agents structured access to Atlarium freshwater aquarium, plant, and habitat data.
Query Codeforces competitive programming platform data including user profiles, contest results, problem statements, and submission history.
Compares package versions across 350+ Linux distributions and repositories via Repology.
Retrieve LeetCode user profiles, solved problem counts, and daily challenge details.