[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"tool-related-ru-basementstudio-xmcp":3},{"items":4,"total":92,"page":93,"pageSize":94},[5,30,45,61,77],{"slug":6,"name":7,"categorySlug":8,"summary":9,"description":10,"categoryName":11,"sourceUrl":12,"homepageUrl":-1,"downloadUrl":13,"cliCommand":-1,"primaryLanguage":-1,"license":-1,"stars":14,"forks":15,"trendScore":16,"qualityScore":16,"supportedClients":17,"clients":20,"tags":27,"installCommand":-1,"configSnippet":-1,"useCases":28,"updatedAt":29},"daoyuanli2816-mcp-fence","daoyuanli2816\u002Fmcp-fence","security-testing","Local-first security scanner, MCP protocol inspector, dynamic fuzzer, Docker sandbox, and report generator for Model Context Protocol servers.","Local-first security scanner, MCP protocol inspector, dynamic fuzzer, Docker sandbox, and report generator for servers.\n\nmcp-fence is a developer tool. Point it at your mcp.json (or any running MCP server you wrote) and it will:\n\n1. the config and source for tool poisoning, dangerous startup commands, plaintext secrets, schema gaps, and unauthenticated HTTP transports. 2. the server live over stdio — runs initialize, tools\u002Flist, gathers schemas\u002Fannotations. 3. every tool with schema-aware payloads (path traversal, command injection, SSRF, prompt injection, oversize input, type confusion). Safe by default; opt in to runtime payloads via --toy-mode or --allow-unsafe. 4. any stdio server in Docker with sensible profiles (strict, filesystem-readonly, network-deny, dev). 5. findings as a plain-text table, JSON, SARIF 2.1.0 (for GitHub code scanning), or a fully offline HTML page.\n\nIt is , , and uses . An optional local-LLM judge can talk to a local Ollama or OpenAI-compatible endpoint.","Security testing","https:\u002F\u002Fgithub.com\u002Fdaoyuanli2816\u002Fmcp-fence","https:\u002F\u002Fgithub.com\u002Fdaoyuanli2816\u002Fmcp-fence\u002Farchive\u002FHEAD.zip",36,0,99,[18,19],"claude-desktop","cursor",[21,24],{"slug":18,"name":22,"summary":23,"count":15},"Claude Desktop","Десктопный клиент с поддержкой локальной конфигурации MCP.",{"slug":19,"name":25,"summary":26,"count":15},"Cursor","AI-редактор кода, часто используемый с developer MCP.",[8],[],"2026-09-01T01:42:54.529925",{"slug":31,"name":32,"categorySlug":8,"summary":33,"description":33,"categoryName":11,"sourceUrl":34,"homepageUrl":-1,"downloadUrl":35,"cliCommand":-1,"primaryLanguage":-1,"license":-1,"stars":36,"forks":15,"trendScore":16,"qualityScore":16,"supportedClients":37,"clients":38,"tags":41,"installCommand":-1,"configSnippet":42,"useCases":43,"updatedAt":44},"f1tz-mcp-for-security-python","f1tz\u002Fmcp-for-security-python","This is a Python refactored version of the security tools MCP (Model Context Protocol) server collection, implemented using the FastMCP library.","https:\u002F\u002Fgithub.com\u002Ff1tz\u002Fmcp-for-security-python","https:\u002F\u002Fgithub.com\u002Ff1tz\u002Fmcp-for-security-python\u002Farchive\u002FHEAD.zip",41,[18,19],[39,40],{"slug":18,"name":22,"summary":23,"count":15},{"slug":19,"name":25,"summary":26,"count":15},[8],"{\n  \"mcpServers\": {\n    \"tool-name-mcp\": {\n      \"command\": \"python\",\n      \"args\": [\"\u002Fpath\u002Fto\u002Ftool-mcp\u002Fserver.py\", \"tool-binary\"]\n    }\n  }\n}",[],"2026-08-26T01:16:14.628002",{"slug":46,"name":47,"categorySlug":8,"summary":48,"description":49,"categoryName":11,"sourceUrl":50,"homepageUrl":-1,"downloadUrl":51,"cliCommand":-1,"primaryLanguage":-1,"license":-1,"stars":52,"forks":15,"trendScore":53,"qualityScore":53,"supportedClients":54,"clients":55,"tags":58,"installCommand":-1,"configSnippet":-1,"useCases":59,"updatedAt":60},"fuzzinglabs-mcp-security-hub","fuzzinglabs\u002Fmcp-security-hub","A growing collection of MCP servers bringing offensive security tools to AI assistants. Nmap, Ghidra, Nuclei, SQLMap, Hashcat and more.","Production-ready, Dockerized MCP (Model Context Protocol) servers for offensive security tools. Enable AI assistants like Claude to perform security assessments, vulnerability scanning, and binary analysis.\n\n- covering reconnaissance, web security, binary analysis, blockchain security, cloud security, code security, secrets detection, threat intelligence, OSINT, Active Directory, fuzzing, and more - accessible via natural language through Claude or other MCP clients - - Non-root containers, minimal images, Trivy-scanned - orchestration for multi-tool workflows - with GitHub Actions for automated builds and security scanning\n\nYou must build the images first with docker-compose build before using them.\n\nCopy the example config to your Claude Desktop configuration:\n\n: ~\u002FLibrary\u002FApplication Support\u002FClaude\u002Fclaude_desktop_config.json\n\n: %APPDATA%\\Claude\\claude_desktop_config.json\n\nFor project-level config, copy .mcp.json to your project root.","https:\u002F\u002Fgithub.com\u002Ffuzzinglabs\u002Fmcp-security-hub","https:\u002F\u002Fgithub.com\u002Ffuzzinglabs\u002Fmcp-security-hub\u002Farchive\u002FHEAD.zip",728,93,[18,19],[56,57],{"slug":18,"name":22,"summary":23,"count":15},{"slug":19,"name":25,"summary":26,"count":15},[8],[],"2026-08-30T08:31:30.64579",{"slug":62,"name":63,"categorySlug":8,"summary":64,"description":64,"categoryName":11,"sourceUrl":65,"homepageUrl":-1,"downloadUrl":66,"cliCommand":-1,"primaryLanguage":-1,"license":-1,"stars":67,"forks":15,"trendScore":68,"qualityScore":68,"supportedClients":69,"clients":70,"tags":73,"installCommand":-1,"configSnippet":74,"useCases":75,"updatedAt":76},"promptfoo-evil-mcp-server","promptfoo\u002Fevil-mcp-server","⚠️ : This MCP server simulates malicious behaviors for security testing purposes only. Do not use in production environments.","https:\u002F\u002Fgithub.com\u002Fpromptfoo\u002Fevil-mcp-server","https:\u002F\u002Fgithub.com\u002Fpromptfoo\u002Fevil-mcp-server\u002Farchive\u002FHEAD.zip",31,90,[18,19],[71,72],{"slug":18,"name":22,"summary":23,"count":15},{"slug":19,"name":25,"summary":26,"count":15},[8],"{\n  \"mcpServers\": {\n    \"evil-mcp-server\": {\n      \"command\": \"node\",\n      \"args\": [\"\u002Fpath\u002Fto\u002Fevil-mcp-server\u002Fdist\u002Findex.js\"]\n    }\n  }\n}",[],"2026-08-30T01:12:19.094729",{"slug":78,"name":79,"categorySlug":8,"summary":80,"description":81,"categoryName":11,"sourceUrl":82,"homepageUrl":-1,"downloadUrl":83,"cliCommand":-1,"primaryLanguage":-1,"license":-1,"stars":84,"forks":15,"trendScore":68,"qualityScore":68,"supportedClients":85,"clients":86,"tags":89,"installCommand":-1,"configSnippet":-1,"useCases":90,"updatedAt":91},"president-xd-revula","president-xd\u002Frevula","A fully functional and production-grade reverse engineering MCP Server","Connect Claude Desktop, MCP-compatible IDEs, or custom tooling to a broad reverse engineering backend through the Model Context Protocol.\n\n- PE\u002FELF\u002FMach-O via LIEF with hash computation and suspicious indicator detection - Multi-backend support including Capstone (always available), radare2, and objdump for x86\u002Fx64\u002FARM\u002FMIPS\u002FRISC-V - FLOSS integration, regex fallback, 17 classifier patterns (URLs, IPs, crypto, registry keys) - Shannon entropy with sliding window, per-section analysis, and packing detection - DWARF, PDB, LIEF universal; function prologue scanning for stripped binaries - Inline rules, file\u002Fdirectory rules, and community rules support - ATT&CK mapping, MBC behaviors, capability enumeration - Ghidra (headless), RetDec, Binary Ninja with caching\n\n- Full GDB\u002FMI protocol with breakpoints, stepping, registers, memory, backtrace, and heap inspection - Native SB API integration for macOS\u002FLinux debugging - Spawn\u002Fattach, script injection, function interception, memory scan\u002Fdump,...","https:\u002F\u002Fgithub.com\u002Fpresident-xd\u002Frevula","https:\u002F\u002Fgithub.com\u002Fpresident-xd\u002Frevula\u002Farchive\u002FHEAD.zip",75,[18,19],[87,88],{"slug":18,"name":22,"summary":23,"count":15},{"slug":19,"name":25,"summary":26,"count":15},[8],[],"2026-09-11T01:33:02.388116",23,1,5]