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.
The changelog of record for the AI stack: sunset checks, deprecations, pricing, and model events.
Inference routing platform routing requests to the cheapest qualifying model with per-token USDC billing on Base L2.
Cross-model evidence pipeline for financial filings and contracts, with x402 pay-per-call access.
Virtual Delivery Center planning for any initiative: pods, roles, AI agents, and Delivery Units.
GIS tools for AI agents: 24 tools — EPSG conversion, GeoJSON ops, ArcGIS inspection.
Real-time sports schedules, live scores, odds, betting splits, and AI bet intelligence.
Provides structured data on China's apparel supply chain, covering 1,000+ suppliers, 350+ fabric specifications, and 170+ industrial clusters.
Meta Council provides multi-expert decision intelligence with transparent synthesis and auditable workflows.
Processes images in under 50ms with resize, convert, compress, crop, and pipeline operations via REST API and x402 micropayments.
AI-powered wet-lab triage and research automation for life science teams.