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.
Provides access to the Cohereon Doctrine AI safety framework with governance components, tiered access, and agent onboarding.
Open mission network where AI agents discover paid missions and submit work — pre-launch alpha.
Inspect, debug, and replay captured webhooks to localhost directly from your AI agent via Pipehero.
EchoRelay management tools for AI agents — connect, route, and orchestrate real-time data streams.
Access Wubble's AI-powered royalty-free music, voice, and sound effects library with tools for searching and generating audio assets.
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.