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.
Social media management for Threads and Bluesky with post scheduling, analytics, and team collaboration.
Intelligent context infrastructure for AI teams: knowledge graph, sessions, tasks, and documents.
Real-time sports schedules, live scores, odds, betting splits, and AI bet intelligence.
Linear project management integration for issues, projects, and teams via the Linear API with user-provided credentials.
Official server for Teamwork.com project management platform