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.
Discover and search verified deep-tech engineering bounties from any AI agent.
KYA identity verification, trust scoring, and performance bonds for AI agents.
Verified business identity data for 5.5 million entities across 34 countries.
Verified business intelligence for AI agents, covering 5.5M+ entities across 34 countries.
Financial infrastructure for autonomous AI agents with self-custody wallets, USDC transfers, collateralized lending, job marketplace, and price negotiation on Polygon.
Scans URLs for malware, phishing, and security threats using ScanMalware.com.