Security Proxy
MCP gateway: many servers, one policy, lethal-trifecta blocking, PII masking, audit log
Search by the task you want done or the app you use, then filter by category.
Sorted by usage score: GitHub stars, weekly downloads, how recently it shipped, and whether its endpoint answers. Most used is not the same as best.
Reading a card:↓ Downloads per weeki★ GitHub starsiThree pillars: reviews · checks · usageiUpdated = latest version published to the registryi
MCP gateway: many servers, one policy, lethal-trifecta blocking, PII masking, audit log
Local-first memory for AI agents: ground truths, failure firewall, negotiated recall over MCP.
MCP server for dnstwist: detect typosquatting, phishing and brand impersonation domains.
Read-only CVE triage: verdicts from CISA KEV, EPSS and exploit feeds, each reason linked.
MCP server for running Ox Security MegaLinter via mega-linter-runner
AI Agent Firewall. Enforce signed authority before consequential actions. Free API key required.
Security-hardened Excalidraw MCP server with auth, rate limiting, and 14 tools
Scans Cursor/Claude/Windsurf/VS Code MCP configs for unpinned versions, secrets, typosquats
Supply-chain malware scanner and MCP server: vet packages in 15 ecosystems before install, offline.
Audit HTTP cookie security against your local policy. Returns findings without cookie values.
Local credential broker: agents call APIs, SSH and DBs via scoped presets; secrets stay in keychain.
The deterministic attack-surface perception layer for AI security agents
Dependency graph + 24 MCP tools. Impact analysis, simulation, security, agent coordination
Bundle of secret-scanner, dependency-auditor, ssl-inspector, and dns-intelligence
MCP server for Shodan API — device search, IP lookup, DNS, and CVE/CPE queries.
Security layer for AI agents: blocks prompt injection, detects fake packages, scans vulnerabilities.
Security scanner for MCP servers: tool poisoning, shadowing, permissions, secrets, transport.
Production readiness for vibe-coded apps. 52 checks for security, reliability, and performance.
Query OSV.dev for package vulnerabilities and batch-audit dependency lists via MCP.
Input firewall for AI agents: scan text and files before an agent reads them. Local, no network.
MCP server for querying VirusTotal API with comprehensive security analysis tools.
30 security tools for AI agents: phishing links, exposure maps, DNS, SSL, PQC, history, pivots.
Scan Android and iOS apps for security issues: findings, MASVS mapping and pentest reports.