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.
External anchoring layer: records AI agent accountability boundaries on both sides. Content-blind.
Access GBIF species taxonomy, occurrence records, biodiversity datasets, and publisher data via a hosted remote endpoint.
Detects AI-generated images, videos, and audio including deepfakes using the identifAI analysis platform.
Searches the global taxonomic index of ~2.2 million accepted species names.
PubChem NIH chemistry database for querying chemical compounds, biological activities, and molecular properties via Pipeworx.
Queries ISRIC SoilGrids global soil property data via Pipeworx gateway.
Ticketmaster Discovery API for event search, venues, and attractions via a managed MCP endpoint.
Resolve marine species names to WoRMS AphiaIDs and retrieve full taxonomic lineages across multiple languages.
Scans URLs for malware, phishing, and security threats using ScanMalware.com.