[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"tool-related-zh-kenprole-chainguard-mcp":3},{"items":4,"total":105,"page":106,"pageSize":107},[5,33,54,70,88],{"slug":6,"name":7,"categorySlug":8,"summary":9,"description":10,"categoryName":11,"sourceUrl":12,"homepageUrl":-1,"downloadUrl":13,"cliCommand":-1,"primaryLanguage":-1,"license":14,"stars":15,"forks":16,"trendScore":17,"qualityScore":18,"supportedClients":19,"clients":22,"tags":30,"installCommand":-1,"configSnippet":-1,"useCases":31,"updatedAt":32},"0x4m4-hexstrike-ai","0x4m4\u002Fhexstrike-ai","security-testing","HexStrike AI MCP Agents is an advanced MCP server that lets AI agents (Claude, GPT, Copilot, etc.) autonomously run 150+ cybersecurity tools for automated pentesting, vulnerability discovery, bug...","HexStrike AI MCP v6.0 features a multi-agent architecture with autonomous AI agents, intelligent decision-making, and vulnerability intelligence.\n\n1. - Claude, GPT, or other MCP-compatible agents connect via FastMCP protocol 2. - Decision engine analyzes targets and selects optimal testing strategies 3. - AI agents execute comprehensive security assessments 4. - System adapts based on results and discovered vulnerabilities 5. - Visual output with vulnerability cards and risk analysis\n\nWatch the full installation and setup walkthrough here: YouTube - HexStrike AI Installation & Demo\n\nYou can install and run HexStrike AI MCPs with various AI clients, including:\n\nRefer to the video above for step-by-step instructions and integration examples for these platforms.\n\nEdit ~\u002F.config\u002FClaude\u002Fclaude_desktop_config.json:\n\nConfigure VS Code settings in .vscode\u002Fsettings.json:\n\n🔍 Network Reconnaissance & Scanning (25+ Tools)","安全测试","https:\u002F\u002Fgithub.com\u002F0x4m4\u002Fhexstrike-ai","https:\u002F\u002Fgithub.com\u002F0x4m4\u002Fhexstrike-ai\u002Farchive\u002FHEAD.zip","MIT",12791,2616,78,86,[20,21],"claude-desktop","vscode",[23,27],{"slug":20,"name":24,"summary":25,"count":26},"Claude Desktop","支持本地 MCP 配置的桌面客户端。",0,{"slug":21,"name":28,"summary":29,"count":26},"VS Code","可用 MCP Server 支持编程和本地自动化的编辑器生态。",[8,14],[],"2026-08-30T08:28:45.150433",{"slug":34,"name":35,"categorySlug":8,"summary":36,"description":37,"categoryName":11,"sourceUrl":38,"homepageUrl":-1,"downloadUrl":39,"cliCommand":-1,"primaryLanguage":-1,"license":14,"stars":40,"forks":41,"trendScore":42,"qualityScore":43,"supportedClients":44,"clients":46,"tags":51,"installCommand":-1,"configSnippet":-1,"useCases":52,"updatedAt":53},"0xsteph-pentest-ai","0xsteph\u002Fpentest-ai","Open-source AI pentester that proves every finding. Machine oracles re-run each exploit; verified bugs ship a proof capsule you can replay yourself.","⚠️ By installing you accept the AUP and Terms. Full text in Responsible use ↓\n\nptai is an AI-driven pentest tool that re-runs every exploit to confirm it. It runs recon, logs in, and chains findings into multi-step attack paths, but it does not ask you to trust the results. The way TruffleHog confirms a leaked secret by logging in with it, ptai confirms a web finding by re-running the exploit: a finding stays a candidate until a machine oracle reproduces it N out of N, and only then does it earn a VERIFIED badge. Third-party scanner output (nuclei, nikto, zap) is held back until an oracle re-proves it. Scanner noise is what trains teams to ignore their tools, so the report carries only what ptai could prove, each VERIFIED finding with a portable proof capsule you can replay yourself.\n\nToday . On a deliberately-vulnerable test honeypot, 23 findings verify across those classes at . On a stock OWASP Juice Shop, . Runs on your laptop. No cloud, no telemetry.","https:\u002F\u002Fgithub.com\u002F0xsteph\u002Fpentest-ai","https:\u002F\u002Fgithub.com\u002F0xsteph\u002Fpentest-ai\u002Farchive\u002FHEAD.zip",1738,321,75,83,[45,21],"cursor",[47,50],{"slug":45,"name":48,"summary":49,"count":26},"Cursor","常与开发类 MCP Server 搭配使用的 AI 代码编辑器。",{"slug":21,"name":28,"summary":29,"count":26},[8,14],[],"2026-08-30T08:27:41.538251",{"slug":55,"name":56,"categorySlug":8,"summary":57,"description":58,"categoryName":11,"sourceUrl":59,"homepageUrl":-1,"downloadUrl":60,"cliCommand":-1,"primaryLanguage":-1,"license":14,"stars":61,"forks":62,"trendScore":63,"qualityScore":64,"supportedClients":65,"clients":66,"tags":67,"installCommand":-1,"configSnippet":-1,"useCases":68,"updatedAt":69},"basementstudio-xmcp","basementstudio\u002Fxmcp","The TypeScript MCP framework","xmcp is a framework for building and shipping MCP servers with TypeScript. Designed with DX in mind, it streamlines development and lowers the barrier to entry for anyone looking to create and deploy powerful tools on top of the Model Context Protocol ecosystem.\n\nBootstrap your first xmcp application with:\n\nor initialize xmcp on an existing Next.js or Express project with:\n\n⊹ - Tools and prompts are auto-registered from a tools and prompts directory\\ ⊹ - Instant development feedback\\ ⊹ - Toolkit for shipping authentication and custom middlewares\\ ⊹ - Customizable configuration for your MCP server\\ ⊹ - Flexible deployment across any platform\\ ⊹ - Zero-configuration deployment with Vercel\n\n⊹ Visit xmcp.dev to learn more about the project.\\ ⊹ Visit xmcp.dev\u002Fdocs to view the full documentation.\n\nIf you believe you have found a security vulnerability, we encourage you to let us know right away.\n\nWe will investigate all legitimate reports and do our best to quickly fix the problem.","https:\u002F\u002Fgithub.com\u002Fbasementstudio\u002Fxmcp","https:\u002F\u002Fgithub.com\u002Fbasementstudio\u002Fxmcp\u002Farchive\u002FHEAD.zip",1339,95,73,69,[],[],[8,14],[],"2026-08-30T08:27:36.618687",{"slug":71,"name":72,"categorySlug":8,"summary":73,"description":74,"categoryName":11,"sourceUrl":75,"homepageUrl":-1,"downloadUrl":76,"cliCommand":-1,"primaryLanguage":-1,"license":77,"stars":78,"forks":79,"trendScore":80,"qualityScore":81,"supportedClients":82,"clients":83,"tags":85,"installCommand":-1,"configSnippet":-1,"useCases":86,"updatedAt":87},"cisco-ai-defense-mcp-scanner","cisco-ai-defense\u002Fmcp-scanner","Scan MCP servers for potential threats & security findings.","A Python tool for scanning MCP (Model Context Protocol) servers and tools for potential security findings. The MCP Scanner combines Cisco AI Defense inspect API, YARA rules and LLM-as-a-judge to detect malicious MCP tools.\n\nThe MCP Scanner provides a comprehensive solution for scanning MCP servers and tools for security findings. It leverages three powerful scanning engines (Yara, LLM-as-judge, Cisco AI Defense) that can be used together or independently.\n\nThe SDK is designed to be easy to use while providing powerful scanning capabilities, flexible authentication options, and customization.\n\n- Run scanner as a stand-alone CLI tool or REST API server - : Use all three scanning engines together or independently based on your needs. - : Scan Python dependencies for known vulnerabilities (CVE\u002FPYSEC\u002FGHSA) using pip-audit integration. - : Zero-dependency static analysis for production readiness issues (timeouts, retries, error handling).","https:\u002F\u002Fgithub.com\u002Fcisco-ai-defense\u002Fmcp-scanner","https:\u002F\u002Fgithub.com\u002Fcisco-ai-defense\u002Fmcp-scanner\u002Farchive\u002FHEAD.zip","Apache-2.0",1089,143,72,81,[21],[84],{"slug":21,"name":28,"summary":29,"count":26},[8,77],[],"2026-08-30T08:30:45.41355",{"slug":89,"name":90,"categorySlug":8,"summary":91,"description":91,"categoryName":11,"sourceUrl":92,"homepageUrl":-1,"downloadUrl":93,"cliCommand":94,"primaryLanguage":-1,"license":14,"stars":80,"forks":95,"trendScore":96,"qualityScore":43,"supportedClients":97,"clients":98,"tags":101,"installCommand":94,"configSnippet":102,"useCases":103,"updatedAt":104},"srajangpt1-ai-security-crew","srajangpt1\u002Fai-security-crew","Security guidance for AI coding agents. Before your agent writes code, it gets the threats to guard against and the fixes to build in. When it adds packages, they are checked and scanned for CVEs.","https:\u002F\u002Fgithub.com\u002Fsrajangpt1\u002Fai-security-crew","https:\u002F\u002Fgithub.com\u002Fsrajangpt1\u002Fai-security-crew\u002Farchive\u002FHEAD.zip","uvx --from git+https:\u002F\u002Fgithub.com\u002FSrajangpt1\u002Fai-security-crew mcp-security-review",26,52,[20,45],[99,100],{"slug":20,"name":24,"summary":25,"count":26},{"slug":45,"name":48,"summary":49,"count":26},[8,14],"{\n  \"mcpServers\": {\n    \"sec-review\": {\n      \"command\": \"uvx\",\n      \"args\": [\n        \"--from\", \"git+https:\u002F\u002Fgithub.com\u002FSrajangpt1\u002Fai-security-crew\",\n        \"mcp-security-review\"\n      ]\n    }\n  }\n}",[],"2026-08-19T23:35:51.450246",29,1,5]