网络安全
从 GitHub 安装到你自己电脑上的开源程序。可查看星标、每周下载量和正在走红的项目。
按使用分数排序:GitHub 星标、每周下载量、最近发布情况和端点是否响应。最常用不等于最好。 批量发布且没有任何星标的发布者不在此标签中,可在“全部”中搜索到。
如何看卡片:↓ 每周下载量i★ GitHub 星标i三大支柱:评价 · 检查 · 使用情况i更新 = 最新版本发布到注册中心的时间i
A2a Trustgate
A2A TrustGate: 4-gate firewall that screens every AI-agent action before it runs. 50 tools.
Fray — WAF Security Testing MCP Server
WAF security testing: 5,500+ payloads, 25 WAF fingerprints, 21 recon checks, bypass AI
Judges Panel
45 judges that evaluate AI-generated code for security, cost, and quality with built-in AST.
Inkog
Security co-pilot for AI agents. Scan for vulnerabilities, audit MCP servers, verify governance.
Apimesh
74 paid web-analysis APIs (SEO, security, TLS, DNS, email) as MCP tools. USDC via x402.
FedRAMP 20x Requirements
An MCP server that provides access to FedRAMP 20x security requirements and controls.
Pincer
Secure grip for your agent's secrets - security-hardened MCP gateway with proxy token architecture
Maskbreak
Public IP signals (cloud hosting, Tor exits) and Maskbreak API status for fraud checks.
Valca
Scans code, IaC and AI-agent config for security problems. Read-only — nothing can be edited.
MySQL (security-first)
Security-first MySQL MCP server with AST validation, table whitelist, schema resources, and audit.
BeVigil OSINT
Discover mobile app attack surfaces via BeVigil OSINT — hosts, subdomains, URLs, and more.
Agent Guardrail
Deterministic policy firewall for AI agent tool calls - YAML rules, not a fuzzy risk score.
Context Firewall
Local MCP proxy: collapses N servers' tools into 4 meta-tools and compresses large tool outputs.
Promptrejectormcp
Security gateway for AI agents: detects prompt injections, jailbreaks, and common vulnerabilities.
Argus
Automated web QA via Chrome DevTools MCP — a11y, security, visual, env diff, CI; Aegis redaction.
Siteaudit MCP
SEO, performance, and security audits for any URL — no API keys required
Active Directory / LDAP
Active Directory / LDAP MCP server: find users, groups, memberships; read-only security audits.
WebSecAuditor AI Cybersecurity & Vulnerability Auditor
Enterprise-grade AI vulnerability auditor for web applications, APIs, and codebases.
Agentrica
56 AI agents for software, design, privacy, security and product work, as MCP prompts.
Véu
Hides personal data and secrets before text reaches an AI and restores them in the answer.
Panda Federation Tools
40 public-data tools for research, US federal funding, B2B leads and web security.
FRITZ!OS 8
FRITZ!Box on FRITZ!OS 8: diagnostics, security audit, devices, Wi-Fi, phone, smart home
aiSecurityWarden
Human approval for AI agents: E2E-encrypted secrets and gated Gmail, GitHub and MCP tools.