Security Proxy
MCP gateway: many servers, one policy, lethal-trifecta blocking, PII masking, audit log
GitHub から自分のパソコンにインストールして使うオープンソースのプログラムです。スター、週間ダウンロード数、注目の伸びを確認できます。
利用スコア順:GitHubスター、週あたりのダウンロード数、最近のリリース、エンドポイントの応答。よく使われている=一番良い、ではありません。 スターがひとつもないまま大量に登録している発行者はこのタブに出ません。「すべて」で検索すると見つかります。
カードの見方:↓ 週あたりのダウンロードi★ GitHubスターi3つの柱:レビュー · チェック · 利用状況i更新=最新バージョンをレジストリに公開した日i
MCP gateway: many servers, one policy, lethal-trifecta blocking, PII masking, audit log
Read-only CVE triage: verdicts from CISA KEV, EPSS and exploit feeds, each reason linked.
MCP gateway: many servers, one policy, lethal-trifecta blocking, PII masking, audit log
AI agent security: 7 MCP tools for injection detection, PII scanning, command safety, DLP.
Security-hardened NotebookLM MCP with post-quantum encryption
Pre-install security scans for npm packages, MCP servers, and AI agents with cited verdict evidence.
Budget, payment and audit controls for AI agent API calls and MCP tool calls.
Check, test, prove and review a rowstile policy: access rules for Postgres row-level security
Audit your own smart-home devices: destinations, encryption, open ports, A-F grade.
Every GuardBee MCP security tool in one server: OWASP MCP Top 10, secrets, supply chain, TLS/DNS
Dockerfile and Kubernetes lint for AI agents: Pod Security Standards, A–F grade, a fix per finding.
Production security for Node.js apps: investigate live attacks, block IPs, tune detections.
Bundle of secret-scanner, dependency-auditor, ssl-inspector, and dns-intelligence
AI threat hunting & incident response for Elasticsearch/OpenSearch with endpoint & network forensics
CyberChef's 504 data-transformation operations as MCP tools: encryption, encoding, forensics.
Input firewall for AI agents: scan text and files before they're read. Local, no network by default.
AI Agent Firewall. Enforce signed authority before consequential actions. Free API key required.
AWS security scanner with attack chain detection, IAM privilege escalation, and fixes
MCP server for Cinema 4D — entity CRUD, parameter-level access, batched undo, security controls.
Security scanning for AI agents: SAST, SCA, secrets, IaC, DAST, ranked by real risk.
Local credential broker: agents call APIs, SSH and DBs via scoped presets; secrets stay in keychain.
ARGUS-3 stdio MCP with WARDEN firewall: argus_ask, argus_status, argus_capabilities.
Security scanner for MCP servers: tool poisoning, shadowing, permissions, secrets, transport.
Open-source AI security agent: SAST, DAST, and policy-as-code over MCP.