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.
Screen names against OFAC, EU, UK, UN sanctions lists; resolve entities via GLEIF. Screening aid.
SIP/VoIP telecom grounding for AI agents with vendor docs, RFCs, and 21 diagnostic utilities.
Agent-first skill marketplace for discovering and installing capabilities across AI platforms.
Query onchain data across EVM, Solana, Bitcoin, Substrate, and Hyperliquid via the SQD Portal API.
Provides access to Drosophila melanogaster neuroscience data including neuroanatomy, neural connectivity, and gene expression from the VirtualFlyBrain knowledge base.
Access Well financial data including invoices, companies, and contacts.
Search and fetch Wikidata entities, execute SPARQL queries, and resolve external identifiers.
Wikiquote collection of quotations from notable people and works, searchable and retrievable via the MediaWiki API.