MCP Safety Warden
MCP proxy adding security scanning, behavioral profiling, risk gating, and safe tool call execution.
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 proxy adding security scanning, behavioral profiling, risk gating, and safe tool call execution.
MCP server: static security scanner for MCP servers, agent skills & plugins. 17 attack patterns.
Agent-safe secrets (local encrypted vault or Vaultwarden): injected into commands, masked in output
Upgrade intelligence for AI agents: what an upgrade changes, where it touches your code, CVE scans.
Scans AI coding sessions and assistant configs for leaked secrets and risky hooks; local, redacted
Record what your AI did as tamper-evident evidence for ISO 42001, EU AI Act and SOC 2. Hash-only.
Agent-first secrets vault. Store, rotate, and share credentials from chat. 20 tools.
OSINT MCP server — 23 tools: DNS, WHOIS, Shodan, breaches, GEOINT, crypto. Works with Claude Code.
Runtime proxy for MCP security, cost governance & audit
Ephemeral data sandbox for AI workflows with guardrails and security
Local code quality and security scanner: lint, types, SAST, SCA, tests, coverage.
VulnCheck exploit intelligence — CVE research, exploit data, advisories, and threat analysis.
HSM-backed vault secrets for AI agents (JIT fetch) plus prompt-injection and threat scanning.
Local security scanner for AI agents: SAST, SCA, secrets, IaC; verifies exploit and fix.
Microsoft Dataverse MCP server: CRUD, FetchXML, metadata, schema, audit, batch and security roles.
4,685 pre-production checks: security, performance, scale, integrations, post-launch, people.
Live threat intelligence: incident clusters, threat actors, CVEs with KEV/EPSS, leak-site victims.
Deploy AI-built internal apps behind your company login, with a database, files and secrets.
Every agent action watched, every money-moving one gated, every verdict independently verifiable.
Scan AI-generated JS/TS for security and reliability issues; score a site for AI-agent readiness.
MCP server teaching AI agents to implement TideCloak: auth, E2EE, IGA, security analysis
DNS and email security: check SPF, DKIM, DMARC, DNSSEC, DANE and build the records. 45 tools.