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.
-
Reference MCP App for Elastic Security — interactive SOC dashboards inside Claude, Cursor, and other MCP hosts.
NOASSERTION ★ 25 -
Security-first, self-hosted MCP and ChatGPT app for multi-mailbox IMAP intelligence with optional policy-gated Safe Send.
Apache-2.0 -
@irfankabir002/workspace-trust-auditorupdated this year
Read-only ChatGPT App and MCP server for local workspace trust, security, and provenance audits.
npm MIT -
Zero-trust control plane for the git-fabric org. GitHub App identity, security automation, and MCP org tooling.
MIT ★ 1 -
Prove the exploit. Fix the app. Re-prove it. Proof-carrying security for vibe-coded apps — MCP-native.
NOASSERTION -
Installs the probekit app security skill and the REA MCP server (Ghidra, JADX, apktool) into your AI agents, such as Claude Code, Codex, Cursor and Gemini CLI. It detects the agents on your machine and lets you pick which ones to set up.
npm MIT -
Bridge ChatGPT securely to your chosen local folders with a native macOS menu-bar app, enabling 65 scoped MCP tools.
-
Native macOS menu-bar app connecting ChatGPT to one scoped local folder through Secure MCP Tunnel and 65 MCP tools.
★ 2 -
mobile-security-mcpgithub.com/Serhatcck/mobile-security-mcpupdated this year
Mobile app security analysis MCP server for Android APK and iOS IPA files
npm MIT ★ 8 -
Evidence-first audits for AI-generated code: prove tests can fail, catch security and release gaps, and ship reviewable receipts across VS Code, JetBrains, CI, MCP, and App Store workflows.
pypi NOASSERTION ★ 5 -
@shipcheck/mcp-serverupdated this year
ShipCheck MCP server — security scanner for vibe-coded apps
npm MIT -
Local-first logbook for building products — incidents, decisions, security findings and deploys, written by you and your AI agent. Desktop app + CLI + MCP server.
MIT ★ 1 -
mcp-web-recon-agentgithub.com/joepangallo/web-recon-agentupdated this year
MCP server for analyst-first owned-target web security assessments of authenticated, high-friction apps
npm UNLICENSED -
Free security & privacy scanner for AI-coded apps. 766 rules, 84 MCP tools, 13-layer defense, zero-trust sandbox, AI firewall. Runs locally, never sends data anywhere. Scan your AI-generated app for leaked keys, open databases, and injection holes in 5 seconds.
npm MIT ★ 7 -
microsoft-security-agent-toolkitgithub.com/vinayaklatthe/microsoft-security-agent-toolkitupdated this year
Action layer for Microsoft Security AI agents - MCP servers, KQL snippets, Logic Apps templates, and end-to-end demos that pair with microsoft-security-skills
MIT ★ 2 -
pluto-aguardgithub.com/arshan846/pluto-aguardupdated this year
Security scanner and launch gate for AI agents & MCP apps — config scanning, policy coverage, risk modeling, drift detection, CI/SARIF, and launch-readiness evidence
Apache-2.0 ★ 4 -
Health check for React Native and Expo apps: upgrade blockers, App Store and Google Play rejections, crash risks, security (OWASP MASVS), accessibility and performance, with a step-by-step upgrade plan.
npm MIT -
Can one customer of your app read another customer's rows? A read-only audit of Postgres and Supabase row level security.
MIT -
gorgon-scout-mcpgithub.com/Gorgon-Cyber/gorgon-scout-mcpupdated this year
Model Context Protocol server for Gorgon Scout: run AI-driven web-app and API security scans from Claude or any MCP agent.
mcpb NOASSERTION -
NoVibeLeaks — MCP security server for vibe-coded apps (secrets, API keys, anti-patterns). PyPI: novibeleaks
MIT -
@ninjascout77/httptoolkit-mcpupdated this year
MCP server for LLM-driven security testing via HTTPToolkit — capture analysis, mutation-based replay, audit trails for mobile and electron app pentesting
npm MIT -
agent-sec-scanactive
Agent security scan MCP. Activate: npx agent-sec-scan --x402 https://scan-api-production-e73f.up.railway.app
npm MIT -
Free, local-first, fingerprint-transparent web security testing workbench in Rust (Camoufox) — a Burp/Caido alternative with a native app, web UI, CLI and built-in MCP
MPL-2.0 -
noxgithub.com/Nox-HQ/noxactive
Open-source security scanner with first-class AI app security (prompt injection, embedding leakage, agent over-privilege, MCP hardening). Polyglot AIBOM, SARIF, SBOM. Cosign-signed plugin marketplace. Offline-first, agent-native via MCP.
Apache-2.0 ★ 11 -
Local-first security architecture knowledge system with traceable data, relationship workbenches, desktop apps, and read-only MCP access.
★ 3 -
Open-source, read-only security checks for apps built with AI: leaked keys, exposed files, open panels, vulnerable Next.js. CLI, GitHub Action and MCP server.
AGPL-3.0 -
the-box-mcpgithub.com/horizonfps/the-box-mcpupdated this year
MCP daemon that gives an agentic coding client a native offensive-security toolchain: MITM proxy, app graph, OOB server, CVE/report RAG and 103 tools.
MIT ★ 2 -
Cybersecurity-MCPgithub.com/LiamTCollins/Cybersecurity-MCPupdated this year
A tool to add to an agent's repertoire to improve security of AI created apps and sites.
Apache-2.0 -
MCP server for Redproof: security checks for apps built with Lovable, Bolt, Cursor and Claude Code
MIT -
vibecheck-scanactive
Zero-trust local security scanner, MCP server & .cursorrules generator for vibe-coded apps
npm MIT -
zngithub.com/usezn/znactive
The local security layer for coding agents. Use Claude Code, Codex CLI, Cursor, OpenCode, Antigravity or the ZCode desktop app without exposing your secrets, your data or your systems. Open source (MIT), no account, nothing sent by default.
npm MIT ★ 5 -
miniOrange Secure WordPress MCP Server: connect Claude, ChatGPT, Grok, Cursor and other AI apps to your WordPress site. 479 tools for content, WooCommerce, SEO, Elementor and forms, with role-based permissions, OAuth 2.1 sign-in and full audit logs. No coding needed.
MIT -
MCP security scanner (CLI + MCP server): detects tool poisoning, prompt injection, and rug-pulls in MCP manifests. Also an OWASP LLM Top 10 prompt-injection/jailbreak CLI for LLM apps.
npm MIT ★ 3 -
argosx-mcpactive
ArgosX MCP server — let your AI coding agent (Claude Code, Cursor, Windsurf) scan your deployed app for security leaks before you ship.
npm MIT -
ybe-checkgithub.com/addycuber/a2k2-ps1updated this year
Production-readiness security gatekeeper for vibe-coded apps — 16 scan modules, AI remediation, MCP server, VS Code extension, and bento dashboard.
pypi Apache-2.0 -
Find the security holes your AI coding assistant just shipped. MCP server + CLI for vibe-coded web & mobile apps: leaked keys, missing Supabase RLS, open Firebase rules, unauthenticated routes, hallucinated packages.
MIT ★ 1 -
Offline cyber security agent for your apps and AI coding tools. Open R&D: measured in public, improved every release.
npm MIT -
ciphragithub.com/sanjayselvam31/ciphraupdated this year
Security scanner for AI-generated apps. Detects exposed API keys, validates them against live services, and exposes itself as an MCP server for AI coding agents.
npm MIT -
Model Context Protocol (MCP) server providing comprehensive cybersecurity intelligence from HUMAN Security. Offers real-time attack monitoring, threat detection, fraud prevention, PCI DSS compliance validation, and supply chain security for AI-powered app
npm MIT -
Model Context Protocol (MCP) server providing comprehensive cybersecurity intelligence from HUMAN Security. Offers real-time attack monitoring, threat detection, fraud prevention, PCI DSS compliance validation, and supply chain security for AI-powered app
npm MIT -
redproof-mcpactive
MCP server for Redproof: security checks for apps built with AI tools. Scan a GitHub repo and read the fix prompts from Claude, Cursor or any MCP client.
npm MIT -
Fast, AI-first web security testing toolkit in Rust: an open-source alternative to ZAP, Burp Suite and the like. Intercepting proxy, scanner, fuzzer and reports, as a JSON CLI with an MCP server and a desktop app.
Apache-2.0 ★ 13 -
Static production-readiness auditor for Flask apps: architecture, templates, deployment, testing, security, database, dependencies and code quality. CLI, pre-commit hook, GitHub Action and MCP server.
pypi MIT -
Android manifest security audit: zero-dependency AXML reader, 40 rules over the surface another app can reach, byte offsets as evidence, SARIF + 7 MCP tools.
MIT -
Security-first MCP server and Windows desktop app for AI-powered system monitoring and process control. Analyze resources, detect unnecessary processes, and act safely with user approval.
Apache-2.0 -
Kotlin MCP server that maps app tech stacks to secure, fully provisioned AWS infrastructure via Terraform (+ Helm for EKS): generate → validate → plan → apply with checkov/kube-score security gating, infracost cost estimation, and drift detection.
MIT ★ 1 -
pincheckgithub.com/cognis-digital/pincheckupdated this year
Validates that a mobile app's TLS pinning, certificate transparency, and network-security-config are actually enforced by replaying a MITM handshake against the built artifact.
NOASSERTION -
Enhanced mobile app automation for AI coding agents. AI-powered selectors, optimized snapshots, streaming MCP, AI screen recording, security scanning, interactive architecture docs. Fork of callstack/agent-device.
MIT -
Free MCP server, Cursor rule and Claude skill that help AI coding assistants avoid common security holes in vibe-coded apps (Supabase RLS, leaked keys). By SealMyApp.
MIT -
Secure Electron desktop app bridging MySQL databases to MCP (Model Context Protocol) AI clients. Features Streamable HTTP, optional ngrok tunnel, UI approvals, and strict SQL guardrails.
Apache-2.0 -
Local-first MCP security scanner for AI-generated apps: four open-source engines plus the Synvoya engine. Scan → fix → rescan from Claude Code, Cursor, Codex, and other agents.
npm Apache-2.0 ★ 51 -
AI-powered Python security analyzer combining Semgrep + MCP for contextual, prioritized vulnerability reports, with a Next.js/FastAPI UI and Terraform deploys to Azure Container Apps and Google Cloud Run.
★ 1 -
One command that checks your whole project before you ship it: security, correctness, accessibility, performance and code health, for any app. Zero dependencies, no telemetry, built for people and AI agents (MCP).
npm NOASSERTION ★ 2 -
AISRF, the AI Security & Research Framework: every LLM request from your apps and agents becomes a ticket a human approves before it reaches the backend. Analyzers, guardrails (Rebuff, LLM Guard, NeMo, Lakera), red teaming (garak, promptfoo, PyRIT), source code review, reports, MCP server.
Apache-2.0 ★ 2 -
vibecheckgithub.com/ArisRhiannon/vibecheckupdated this year
Offline, no-AI "safe to ship?" gate for vibe-coded apps — finds the security mistakes AI coding agents make (secrets, unprotected routes, eval-RCE, SQLi, CORS, JWT, leaked keys). CLI + MCP, agent-runnable.
MIT ★ 2 -
Cyber-Security Agent - A Code Analyzer via Semgrep MCP server and deployed on Azure Container App
-
authenticator_mcpgithub.com/firstorderai/authenticator_mcpupdated this year
A secure MCP (Model Context Protocol) server that enables AI agents to interact with the Authenticator App.
npm MIT ★ 48 -
Honest security checks, in plain language, for apps your people build with AI. Claude Code / Codex plugin and MCP server.
pypi MIT -
Local-first AI security auditor for your own apps: SAST scanners + LLM roles find vulnerabilities with evidence, keep an append-only audit history, and hand verified fix tasks to AI coding agents via MCP. Rust + SQLite, single binary.
MIT -
The Azure DevOps MCP Server provides dynamic tool calling for Azure DevOps services, enabling seamless agentic integration with Copilot Studio MCP tools. Built on FastMCP, it runs as a containerized Python server on Azure Container Apps for secure, scalable remote access.
MIT