Loading…
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.
Retrieves structured EU AI Act compliance logic, ethics modules, and deterministic governance rules for autonomous agents.
Swiss Jass card game encyclopedia, attested and maintained by the Jassverband Schweiz.
Agent runtime platform for running 150+ AI applications across image, video, audio, LLMs, and 3D.
AI-powered ENS name intelligence with search, valuation, and trading tools across 3.6M+ Ethereum Name Service domains.