Context Firewall
Local MCP proxy: collapses N servers' tools into 4 meta-tools and compresses large tool outputs.
按你想完成的任务或你使用的应用搜索,再按分类筛选。
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。
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
Local MCP proxy: collapses N servers' tools into 4 meta-tools and compresses large tool outputs.
Security gateway for AI agents: detects prompt injections, jailbreaks, and common vulnerabilities.
Automated web QA via Chrome DevTools MCP — a11y, security, visual, env diff, CI; Aegis redaction.
SEO, performance, and security audits for any URL — no API keys required
Read Midge bug reports: video, console logs, network requests and user actions, secrets redacted.
FRITZ!Box on FRITZ!OS 8: diagnostics, security audit, devices, Wi-Fi, phone, smart home
Real-time prompt injection filtering, MCP payload inspection, and A2A trust scoring.
Human approval for AI agents: E2E-encrypted secrets and gated Gmail, GitHub and MCP tools.
Package CVE advisories and manifest audit via x402. Free sample: /v1/sample
Prompt-injection firewall for AI agents: scan untrusted text, fence it, gate tool calls.
Active Directory / LDAP MCP server: find users, groups, memberships; read-only security audits.
Read-only Active Directory / LDAP: users, groups, memberships and security audits.
Domain health and security report: DNS, SSL/TLS, RDAP/WHOIS, SPF/DMARC/MTA-STS, HTTP/HSTS.
Hides personal data and secrets before text reaches an AI and restores them in the answer.
Pay-per-call agent security (x402): injection, tools, shell/SQL, memory, leaks, docs, safe reads
Audit MCP servers for tool poisoning, rug pulls and supply-chain risk (OWASP MCP Top 10).
56 AI agents for software, design, privacy, security and product work, as MCP prompts.
Scan a deployed site for an exposed Supabase service_role key and audit Row Level Security.
Large files and secrets between people and agents, never through the chat or the model.
OWASP API Top 10 tests from your OpenAPI spec, plus scanner SARIF judged for release.
Honeypot threat intel: IOCs, sample comparisons, evidence clusters and ThreatDrop case status.
Every Action1 endpoint, plus fleet-wide patch and vulnerability views across all your organizations.
Passive security audit of a public website: HTTPS, headers, cookies, TLS, DNS, email, security.txt
Paste HTTP response headers and get seven security checks with copy-paste fixes. No fetching.