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 runtime controls on live MCP traffic (Free / Pro $49 / Team $399). Do not equate Andrax grades with Guard 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.
Real-time USGS earthquake feed with filtering by magnitude and timeframe.
Real-time financial and fintech data integration for AI agents via hosted MCP server.
IP geolocation lookups for individual or batched IP addresses via ipwho.is.
DNS lookups via Google DNS-over-HTTPS, covering A, AAAA, MX, TXT, CNAME, and NS records.
Search and analyze 85.7M judicial decisions across 90 jurisdictions with citation network analysis and legal risk assessment.
AI-native scheduling and booking with availability checking, meeting booking, and link sharing.
Real-time macroeconomic signals for AI trading agents with 86 FRED series and deterministic regime classification.
Korean-Japanese bilingual community — read public posts and comments, and route Korea/Japan queries.
Zero-knowledge memory layer for AI agents with differential privacy and AES-256 encryption.
Cross-model evidence pipeline for financial filings and contracts, with x402 pay-per-call access.
B2B company and contact data enrichment across 375M+ companies with corporate hierarchy mapping.
Unified hub for accessing all MCPBundles tools in one place