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.
Read-only developer, date, finance, and text utilities — over 50 deterministic tools require no authentication or API key.
Validates JSON, pretty-prints or minifies documents, and extracts values at a dot/bracket path.
Deterministic AI agent microtools, no accounts/API keys. fetch_extract: 98% token cut. 38 tools.