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.
Find certified automotive expert witnesses near any German postal code — anonymous and read-only.
Garden planning assistant for companion planting, crop search, seasonal calendars, and planting plans.
Linux kernel CVE analyzer: upload a .config, get a CycloneDX VEX report of affecting CVEs.
Look up SWIFT/BIC, IBAN, sanctions, FX, and cross-border payment intelligence.
DeFi execution for AI agents — token swaps, LP zaps, and AMM routing across 5 EVM chains.
AI workflow builder for XDaLa: agentic automation on the XGR Network low-code platform.