Check PyPI and npm upgrades: known vulnerabilities, the safe version, and what each upgrade breaks.
DeepSeek Harness 插件:一键 OAuth 授权连接企查查(Qichacha)法律数据 MCP(法律产品:法规/reg 案例) / One-click OAuth connect to Qichacha Legal MCP (regulation & case)
Read-only access to your Auditon vulnerability scans: findings, endpoints, reports and changes.
Google OAuth Credential Service
FLUSYS-native AI assistant: JWT + IAM wired mcp-core chat, tools, pinned results, chat history
Run scoped, authorized Sn1per pentest, recon and attack surface scans from AI agents; read findings.
TypeScript SDK for applications relying on a CIRCLE auth-service identity provider: OIDC sign-in (backend-for-frontend), entitlements, billing, credit wallet and LiteLLM gateway.
Improve AI-generated code quality with prompt-based analysis across 10 dimensions, from complexity to security vulnerabilities.
Protect an MCP server with Authio, on top of @hyper.authio/server: token validation, protected resource metadata (RFC 9728), WWW-Authenticate challenges with step-up, per-tool authorization and connec
Draft SOC 2 policies from your AI assistant, via MCP
npm MCP — search packages, bundle sizes, vulnerabilities, compare downloads.
Read-only MISP threat intelligence (events, attributes, search, tags, feeds, galaxies) with prompt injection scanning of every response.
Audits security headers + TLS (HSTS, CSP, cert, cookies) for any site. $1.50/call via x402.
Security tools for your AI: scan, pentest, check headers, guard code and scan repos for secrets.
Visual CVE audit dashboard for npm, Python, Go and Rust using OSV data, with browser-based human review and fixes applied only after confirmation.
Security scanner MCP server for AI coding agents. Prompt injection firewall, package hallucination detection (4.3M+ packages), 1700+ vulnerability rules with AST & taint analysis, LLM-powered semantic
Audit a domain's email and web security: SPF, DKIM, DMARC, MTA-STS, DNSSEC, TLS, WHOIS. No API keys.
A containment layer for AI agents that go rogue. Wraps stdio MCP servers: risky tool calls wait for a person, no API key can decide a hold (not even the agent's), and claimed accounts get signed, offl
Black Duck MCP brings Signal's AI-powered security analysis directly into your development environment. Provides vulnerability detection through the Model Context Protocol.
Host-scoped local credential storage shared by Rolino's Node.js adapters
Honeypot detection & token risk scan for ERC-20s. Risk score 0-100, tax, source verification.
Pay-per-call OSINT for AI agents: username + email recon in USDC on Base via x402.
See every file that controls your AI coding agents, what each one tells them to do, which settings put your machine at risk, and whether anything they run is known malware. Runs on your computer.
Free MCP hooks + x402 security scans; MCP manifest and SKILL.md audits cost $0.003 Base USDC.
Experimental MCP extension for proactive third-party OAuth readiness discovery on local stdio servers.
CISA Known Exploited Vulnerabilities feed + remediation deadlines for US federal + critical infr...
完整目錄
IAM、掃描與機密管理。共 1,358 個伺服器,最常用的排在前面。每個都會開啟發布者的頁面。