MCP servers that ship as code — a repository or a package you install and run locally (usually over stdio). They have no hosted endpoint, so we cannot probe or grade them: instead each one shows its repository, install command, license, stars and when it was last updated.
Collected from GitHub repositories and npm, PyPI, Cargo, Go, Maven, NuGet and RubyGems packages tagged as MCP servers, the official MCP Registry, Docker's MCP catalog, ModelScope, Baidu MCP World, Cline and other public directories; one entry per repository. A server that also offers a hosted endpoint is listed under Remote instead. These entries are not counted in our reachability, verification or readiness statistics.
-
Cefense MCP — prove every handler touching req.* (sqli/idor/xss/ssrf) with exploit→mutate→verify
npm MIT -
mcp-api-pentestgithub.com/josenieto/mcp-api-logic-pentestupdated this year
MCP server for autonomous API logic penetration testing — OWASP API Top 10 / BOLA-IDOR detection via LLM-driven analysis
pypi MIT -
webmcp-scannergithub.com/ElonMusk2002/webmcp-scannerupdated this year
Chrome extension that discovers WebMCP tools on a page and flags IDOR, prompt injection, missing consent gates, and over-broad schemas.
-
@boldsec/mcpgithub.com/sahith59/boldupdated this year
BoLD MCP server: connect, wire, and verify BoLD live BOLA/IDOR monitoring from your AI editor (Claude, Cursor, Codex). Metadata only; never reaches a verdict.
npm UNLICENSED -
Local-first AI security & pentesting platform via MCP — Rust static scanner + Python MCP server with WSTG playbooks, RBAC/IDOR matrix & SARIF export.
MIT -
Point an app at two logged-in users and it finds the broken access control (IDOR). Deterministic browser perception + cross-identity authz testing for AI agents — drives your real Chrome over MCP or runs headless. Open-core, local, no account.
npm Apache-2.0 ★ 3 -
mcp-api-pentestgithub.com/josenieto/mcp-api-pentestupdated this year
MCP server for autonomous API logic penetration testing. AI-driven detection of OWASP API Top 10 vulnerabilities (BOLA/IDOR) via multi-session authorization comparison. Supports Bearer, Basic, API Key, Cookie auth. Generates Markdown security audit reports with evidence.
MIT ★ 1 -
Vulnerable-by-design MCP server for learning object-level / cross-tenant authorization (BOLA/IDOR) bugs, plus Semgrep rules that find the same shapes in JavaScript/TypeScript, Python, Go, Rust, Java, Kotlin, C#, PHP, Ruby and Swift MCP servers - shipped as a GitHub Action with SARIF output.
MIT -
authmatrixgithub.com/cognis-digital/authmatrixupdated this year
Test an access-control matrix (role x endpoint) for IDOR/authz gaps
NOASSERTION -
Authorized Android pentest lab, drivable by hand or by AI — Frida bypass chain, live traffic capture with automatic IDOR flagging, full MCP control plane, web dashboard.
MIT ★ 9 -
Static analysis scanner for multi-tenant SaaS and MCP server code. 57 deterministic rules for cross-tenant data leakage, IDOR, RLS, and MCP-specific risks. Includes MCP server, SARIF output, and GitHub Action.
npm MIT ★ 5 -
AI-powered MCP server for Burp Suite Professional — 149 tools across proxy, scanner, inline fuzzer, race conditions, guided injection, JWT/IDOR attacks, recon & OOB, with a real-time dashboard and hardened localhost security. Drive Burp from Claude Code or any MCP client.
MIT ★ 308 -
Luvv-MCP 是一个 AI 原生的前端安全分析引擎,接入 Claude Code 后,你说一句"帮我审计这个网站",AI 就能自动完成技术栈识别(1.8 万条规则覆盖 CMS/框架/CDN/中间件)、泄露扫描(阿里云 AK、GitHub Token、Webhook、JWT 等 60+ 类敏感信息)、漏洞审计(XSS、开放重定向、CSRF、IDOR、硬编码密码 6 类自动检测)、产品指纹识别(HTTP 响应头/Body/Favicon Hash 多维匹配),还能自动发现 SourceMap 并还原混淆源码。核心价值:把 SRC 挖洞和授权渗透中"人工看 JS 源码找漏洞"的环节从 30 分钟压缩到 30 秒,一行 JSON 配置即可使用。
MIT ★ 42 -
@felix-neuro/routeguardgithub.com/felixmatrixar/routeguardupdated this year
OWASP API security analysis for Node.js backends — ESLint plugin + AI agent + MCP server
npm MIT -
framesevengithub.com/sayseven7/framesevenupdated this year
Offensive web security scanner — OWASP Top 10 · MCP server · CLI · Go
MIT ★ 13 -
break-anything-mcpactive
Autonomous Chaos & Exploit Agent for Vibe-Coded Apps. Finds race conditions and auth bypasses before hackers do.
npm MIT -
hackbrowser-mcpgithub.com/badchars/hackbrowser-mcpupdated this year
The first browser MCP built for security testing. Give your AI agent a real Firefox browser and let it find vulnerabilities.
MIT ★ 24 -
CLI-first, agent-native HTTP intercepting proxy & bug bounty toolkit. Headless Burp Suite alternative for AI agents (MCP), penetration testers, and ethical hackers with declarative YAML scope enforcement.
MIT ★ 2