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 allow/deny/audit on live MCP traffic (mcpgrade-2.0.0). Do not equate the two 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.
Hosted persistent memory with semantic search, importance scoring, and TTL for AI agents.
AI tool discovery from the TrueAI catalog, covering 1,600+ AI SaaS apps with reviews and sub-scores.
Secure file transfer MCP server that relays files between AI agents and downstream services using bearer-token authentication.
Douyin hot search, work search/details, comments/replies, profiles, series, transcript.
Kuaishou short-video data via SocialDataX — hot lists, video details, creator profiles, and comments.
Macro-factor quantitative trading signal source with live strategy performance data and AI-native signal delivery.
WeChat Channels hot search, video search/details, comments/replies, users, and transcript.
Weibo hot search, post search/details, comments/replies, users, posts, and transcript.
XHS (Xiaohongshu) MCP for note search, hot list, post details, comments/replies, profiles, and transcript.