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.
Book London furniture assembly, wall mounting, handyman, electrical, and smart home jobs.
EU Horizon Europe grant search, project intelligence, and consortium-partner matching over CORDIS data.
Unified gateway to Algeria's TKAWEN ecosystem: commerce, certification, and AI tools.
Polish B2B software house offering AI agent access to project tools and methodology via public and OAuth-secured endpoints.
Made-to-order data for AI agents: company intel, B2B contacts, scraping. Pay per call via x402.
Access structured education data and institutional records through a BrightKey MCP endpoint.
Try 26 utility REST APIs keylessly: NAICS classification, IP geo, email validation, currency.
Searches Russian construction and real estate companies, house projects, and pricing across major cities.
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.