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.
-
MCP server for running source code security reviews with an LLM
Apache-2.0 -
Security MCP server for AI agents — native per-language analysis: Kotlin (detekt), Java (SpotBugs), Python (Bandit), C# (Roslyn); diff review; secure patterns
pypi MIT -
saltcodegithub.com/Secful/saltcodeupdated this year
Give your coding assistant security super powers with Salt Code. Secure code with every prompt and a much quieter security team.
MIT ★ 1 -
Claude Code security plugin and agentskills.io skill pack for securing LLM agents: threat modelling, config audits, prompt injection review, MCP server review, incident lookup, security evals, Semgrep rules, guard hooks and an incident-database MCP server.
MIT -
Security scanner MCP server for AI coding agents. Prompt injection firewall, package hallucination detection (4.3M+ packages), 1000+ vulnerability rules with AST & taint analysis, auto-fix.
go MIT ★ 123 -
cleaner-codegithub.com/goldmembrane/cleaner-codeupdated this year
AI code security scanner MCP server — detects invisible Unicode, Trojan Source, homoglyphs, Glassworm steganography, rules file backdoors, and dependency attacks in AI-generated code. Static analysis + CodeBERT deep learning. Runs locally.
npm MIT ★ 1 -
secure-actionsgithub.com/Kota-Karthik/secure-actionsupdated this year
MCP server for secure AI agent authentication — lets Claude, Claude Code, and other LLM agents call APIs without exposing raw tokens or credentials to the model
Apache-2.0 ★ 3 -
Adversarial Co-Generation Engine — concurrent Builder+Breaker agents for production-grade AI code security
pypi MIT ★ 1 -
Your coding agent builds the site; this makes it prove the site is secure before you ship. 102 checks, evidence and fixes. Skill + MCP server for Claude Code, Codex, Cursor.
MIT ★ 1 -
Local security fence and GitHub Action for AI coding agents — detect secrets, risky commands, and unsafe network actions before they run.
npm Apache-2.0 -
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 -
@vettiq/mcp-servergithub.com/lumeniqjs/vettiq-platformupdated this year
VettIQ MCP server — security scanning for AI-generated code, callable from Cursor, Claude Code, and any MCP-compatible agent.
npm UNLICENSED -
Scan and fix vulnerabilities in Python, JavaScript, TypeScript, Go, and Java code using AI-powered analysis with 200 built-in security rules.
MIT ★ 2 -
nightprismgithub.com/Ammmaze-Ltd/nightprismupdated this year
MCP-native security scanner that asks "should I ship tonight?" for AI-generated code.
Apache-2.0 -
Security infrastructure your AI can't be — deterministic, current past your model's training cutoff, whole-repo-aware, author-independent. Security MCP for vibe coding. 670 rules, 39 tools, CLI + doctor. Prompt-level shift-left security (secure_prompt — e
npm Apache-2.0 -
code-firewall-mcpgithub.com/egoughnour/code-firewall-mcpupdated this year
A structural similarity-based code security filter for MCP (Model Context Protocol). Blocks dangerous code patterns before they reach execution tools by comparing code structure against a blacklist of known-bad patterns.
pypi MIT -
Security help for defenders: grade your site's security headers (fixes + README badge) and read logs/code to find what happened. Claude Code plugin, MCP server, no install.
mcpb MIT ★ 1 -
Security rules for AI coding agents: 681 rules, 21 platforms, MCP server, Claude Code plugin. Web, mobile, databases, cloud, AI, banking.
MIT -
zeropath-agent-plugingithub.com/ZeroPathAI/zeropath-agent-pluginupdated this year
ZeroPath plugin for AI code agents — bring AppSec scanning (SAST, secrets, SCA, IaC), finding triage, and security context into Claude Code from chat.
MIT -
mcp-secopsgithub.com/menviv/mcp-secopsupdated this year
Security operations as conversation. An MCP server connecting 13 security platforms (Wiz, Kodem, GitHub, Okta, SentinelOne, Apono, Twingate, Pluto, Panorays, Abnormal, Slack, Monday, Jenkins) to Claude Code. 102 tools. MIT.
MIT -
SkillSync MCP — security-gated skill management for Claude Code, OpenClaw, Cursor & Windsurf. 60+ threat pattern scanner.
npm MIT ★ 4 -
bastiongithub.com/BintangDiLangit/bastionupdated this year
Local-first security scanner for developers and AI coding agents — deterministic SAST with stable finding fingerprints, baseline deltas, suggested fixes, and an MCP server.
go MIT -
MCP security scanner — source code audit with 25+ Semgrep rules, config health checks, SARIF output for CI/CD
pypi MIT -
@arcwall/mcp-servergithub.com/rom-baro/arcwall-mcpupdated this year
Arcwall Security MCP server for Claude Code, Cursor, Windsurf and any MCP-compatible AI coding tool
npm MIT -
MCP server giving AI coding agents (Claude Code, Codex, Cline) safe, structured network & security recon tools — DNS, WHOIS, TLS, and HTTP security headers, each with a graded verdict. Authorized testing & education only.
pypi MIT ★ 1 -
Open-source security inspection for MCP configurations and tool metadata. Run locally from the CLI or inside your coding assistant.
npm MIT ★ 3 -
MCP server (not a Claude Code Skill) for the VibeSafe security scanner — scan code, live URLs and run a Launch Check from Claude Desktop, Claude Code, Cursor, Windsurf or any MCP client.
MIT -
agent-skill-scan-mcpgithub.com/rexcoleman/agent-skill-scan-mcpupdated this year
MCP server: Scan OpenClaw SKILL.md and MCP tool definitions for security vulnerabilities. 22 rules. For Claude Code.
MIT -
Legacy MCP security server — superseded by correctover-mcp-gateway for Claude Code, Cursor, Cline and Windsurf. Install the gateway instead; the runtime SDK is the correctover package.
npm LicenseRef-Proprietary -
IntentShield for MCP: an offline-first security guardrail against prompt injection in MCP tool calls, with hooks for Claude Code, Codex CLI, Cursor and Gemini CLI and a transparent MCP proxy
pypi Apache-2.0 -
NoVibeLeaks — MCP security server for vibe-coded apps (secrets, API keys, anti-patterns). PyPI: novibeleaks
MIT -
gadriel-claude-pluginsgithub.com/Gadriel-ai/gadriel-claude-pluginsupdated this year
Gadriel AI Security Harness plugins for Claude Code — local SAST, SCA/SBOM, secrets & OWASP LLM security scanning via MCP.
-
Gadriel AI Security Harness for Claude Code — local SAST, SCA/SBOM, secrets, container, config & OWASP LLM security scanner via MCP.
Apache-2.0 -
MCP security server for AI agents — runtime verification and receipt verification for Claude Code, Cursor, Cline and Windsurf. 7-dimension CCS checks, Ed25519 tamper-evident receipts, offline verification, zero runtime dependencies.
npm Elastic-2.0 -
deca-guard-mcp-servergithub.com/tomtarpey/deca-guard-mcp-serverupdated this year
MCP Server for code smell and security analysis
npm MIT -
Gadriel AI Security Harness for VS Code — local SAST, SCA/SBOM, secrets, container, config & OWASP LLM security scanner and MCP server.
Apache-2.0 -
Security & Observability for AI Agents — audit every tool call, enforce allow/block policies, catch prompt injection and data leaks. Local-first; works with Claude Code, Codex, Copilot CLI, OpenClaw, LangChain, and all major LLM APIs.
npm NOASSERTION ★ 15 -
burp-mcpgithub.com/Den-Sec/burp-mcpupdated this year
Burp Suite Professional MCP server - 61 tools to drive Burp from an AI agent (Claude Code) for authorized security testing.
MIT ★ 3 -
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 -
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 -
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 -
Securely feeds summarized expert security rules into your coding assistance Claude Code, Cursor, etc — zero config, no API key.
NOASSERTION -
truss-code-review-mcpgithub.com/claw-factory/truss-code-review-mcpupdated this year
AI-powered code review tools for Claude Code — complexity analysis, anti-pattern detection, security review, and optimization
npm MIT -
appwrite-security-mcpgithub.com/Perufitlife/appwrite-security-mcpupdated this year
MCP server for Appwrite security audits inside Claude Code, Cursor, Cline.
npm MIT -
Offline security scanning for AI-generated code: seven open-source scanners and AI-specific checks in one command. It finds secrets, vulnerable, hallucinated and malicious dependencies, poisoned agent configuration, and infrastructure and code flaws. An MCP server for Claude Code and Kiro, and a CLI. Your source never leaves your machine.
pypi Apache-2.0 -
MCP server for Airlock — let an AI coding agent (Cursor, Claude) scan a deployed site for an exposed Supabase service_role key and audit Row Level Security, mid-build. Catches the #1 vibe-coding leak.
npm MIT -
Production-grade diagnostics, performance optimization, security auditing, and dead-code detection for Vue.js and Nuxt applications. Features automated codemods, CI quality gates, and AI agent integration (MCP).
npm MIT -
npmguard secure AI agents auto-edits flows by screening every npm package for known-malicious code and typosquats before anything runs, in Claude Code, Cursor and Codex over MCP or the CLI. one Rust binary, off npm on purpose.
MIT ★ 2 -
Security layer for AI agents: real-time interception of pip/npm/cargo/gem/go installs via Hermes & OpenClaw plugins, Claude Code/Codex hooks, MCP, shell guard, PATH shim, execve, and index proxy. Checks CVEs (OSV/NVD/GitHub), typosquats, malware, licenses, provenance, trust, lockfile hashes. Offline mirror, hash-chained audit, SBOM/SARIF.
MIT ★ 4 -
Governance layer for AI coding agents — model routing, security scanning, tamper-evident audit trail, JIT permissions. MCP server, 142 tools, 83 skill packs, 14 agent hosts, MIT licensed.
MIT -
@kevinrabun/judgesgithub.com/kevinrabun/judgesupdated this year
45 specialized judges that evaluate AI-generated code for security, cost, and quality.
npm MIT -
firebase-security-mcpgithub.com/Perufitlife/firebase-security-mcpupdated this year
MCP server for Firebase Firestore Rules security audits inside Claude Code, Cursor, Cline.
npm MIT -
supabase-security-mcpgithub.com/Perufitlife/supabase-security-mcpupdated this year
MCP server for Supabase security: audit, apply fixes, re-audit from any MCP client (Claude Code, Cursor, Cline).
npm MIT ★ 1 -
Dockerized HexStrike AI on a linuxserver.io Kali base image, with a remote streamable-HTTP MCP server exposing 150+ offensive-security tools to MCP clients like Claude Code.
-
@iflow-mcp/kevinrabun-judgesgithub.com/kevinrabun/judgesupdated this year
45 specialized judges that evaluate AI-generated code for security, cost, and quality.
npm MIT -
CodeScopegithub.com/yashisrani/CodeScopeupdated this year
AI-powered TypeScript & JavaScript code analysis for complexity, security, dead code, and dependencies - 100% offline, built for MCP.
Apache-2.0 ★ 1 -
vibesafegithub.com/stef41/vibesafeupdated this year
AI-generated code safety scanner for the vibe coding era. Catches hallucinated imports, hardcoded secrets, security vulnerabilities, and dead code. CLI + Python API.
NOASSERTION ★ 1 -
vibecheck-scanactive
Zero-trust local security scanner, MCP server & .cursorrules generator for vibe-coded apps
npm MIT -
MCP server for SixthWall AI code security scanner. Integrates with Claude Code for automatic vulnerability detection with Fix Packs.
npm UNLICENSED -
judgesgithub.com/KevinRabun/judgesupdated this year
MCP server with specialized judges to evaluate AI-generated code for security, cost, scalability, cloud readiness, and best practices.
npm MIT ★ 7