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-security-toolkitgithub.com/x0base/mcp-security-toolkitupdated this year
Atomic MCP tools for AppSec and AI Security engineers
pypi MIT -
mcp-security-toolkitgithub.com/x0base/mcp-security-toolkitupdated this year
13 atomic MCP tools for AppSec and AI Security: recon, MCP audit, prompt-injection audit, OWASP LLM Top 10
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 -
open-source-software-supply-chain-mcpgithub.com/apifyforge/open-source-software-supply-chain-mcpupdated this year
Open source supply chain risk assessment for AppSec teams, engineering leads, and platform engineers who need more than a CVE scanner. This MCP server aggregates 7 live data sources — GitHub, NVD, CISA KEV, StackExchange, Hacker News, Federal Register, and Congress.
MIT -
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 -
Open-source MCP server for querying ZeroPath security issues, patches, and scans using Claude, Cursor, Windsurf, or any AI assistant.
MIT ★ 11 -
Self-hosted security scanner, autonomous pentest & QA agent, and production-readiness gate
AGPL-3.0 -
Dependency vulnerability scanner over OSV.dev with CISA KEV actively-exploited flags. No API key.
-
vaktgithub.com/Vaktex/vaktactive
Open-source AST aware code scanner to find your app’s vulnerabilities.
NOASSERTION ★ 1 -
Security linter for environment variables, Docker, CI, Kubernetes, and runtime configuration.
MIT ★ 4 -
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.
-
Find payment logic flaws in Razorpay and Stripe checkouts - client-trusted amounts, rupee/paise bugs, unverified webhooks
MIT ★ 1 -
Gadriel AI Security Harness for Claude Code — local SAST, SCA/SBOM, secrets, container, config & OWASP LLM security scanner via MCP.
Apache-2.0 -
Connect Claude Code or Cursor to PreHack, the autonomous AI pentester. Device-code login, no API key.
Apache-2.0 -
opzyai-mcpgithub.com/thfothijn/opzyai-mcpupdated this year
Local-first security check MCP server for AI coding agents — hardcoded secrets, .env exposure, git-history leaks, dependency CVEs. Runs entirely on your machine.
MIT -
Gadriel AI Security Harness for OpenAI Codex — local MCP server and hooks for SAST, SCA/SBOM, secrets & OWASP LLM security scanning.
Apache-2.0 -
Gadriel AI Security Harness for Cursor — local MCP server, rules, and edit hooks for SAST, SCA/SBOM, secrets & OWASP LLM security scanning.
Apache-2.0 -
Gadriel AI Security Harness for VS Code — local SAST, SCA/SBOM, secrets, container, config & OWASP LLM security scanner and MCP server.
Apache-2.0 -
Gadriel AI Security Harness for GitHub Copilot — local MCP server, prompts, and instructions for SAST, SCA/SBOM, secrets & OWASP LLM security scanning.
Apache-2.0 ★ 2 -
MCP server for reading your EyalSec security events, machines, runs and rules from Claude, Cursor or any MCP client.
MIT -
Security rules for AI coding agents: 681 rules, 21 platforms, MCP server, Claude Code plugin. Web, mobile, databases, cloud, AI, banking.
MIT -
Game/desktop binary integrity scanner that fingerprints executables, detects common packers/obfuscators, and diffs against a known-good baseline to catch tampering.
NOASSERTION -
ipasnitchgithub.com/cognis-digital/ipasnitchupdated this year
Static scanner for iOS .ipa bundles that flags ATS exceptions, missing entitlements hardening, embedded URLs/secrets, and weak Info.plist transport settings.
NOASSERTION -
cheatsensegithub.com/cognis-digital/cheatsenseupdated this year
Anti-cheat telemetry analyzer that ingests game session logs and flags statistically anomalous input/aim/movement signatures with explainable per-flag scoring.
NOASSERTION -
MCP server for the BeVigil OSINT API — mobile app attack surface discovery (hosts, subdomains, S3 buckets, wordlists) for AI agents
npm MIT -
deeplinkfuzzgithub.com/cognis-digital/deeplinkfuzzupdated this year
Fuzzes Android/iOS deep links, intents, and custom URL schemes against an emulator/device to surface unvalidated-redirect, injection, and component-hijack bugs.
NOASSERTION -
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 -
apkpeekgithub.com/cognis-digital/apkpeekupdated this year
One-command static triage of Android APK/AAB binaries: surfaces hardcoded secrets, exported components, dangerous permissions, and insecure manifest flags as a single SARIF report.
NOASSERTION -
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 -
Self-hosted application security platform: SAST, DAST and SCA with AI false-positive validation. OWASP Top 10/CWE mapping, SBOM export, CI/CD integrations and MCP server.
MIT ★ 1 -
Know what changed inside your Electron release: diff two builds for IPC, preload, windows, fuses and hosts, with file:line. CLI, CI gate, MCP server.
npm MIT ★ 10 -
A headless, config-as-code DAST runner that crawls an authenticated web/mobile-API surface and fires a curated active-scan ruleset, emitting deduplicated SARIF.
NOASSERTION -
Generates a CycloneDX SBOM for mobile apps by unpacking native libs and bundled SDKs, then matches components against known-vuln and tracker/privacy databases.
NOASSERTION -
semsiftgithub.com/cognis-digital/semsiftupdated this year
Lightweight semantic-aware SAST that runs curated taint rules over diffs only, so PRs get fast incremental SAST instead of whole-repo scan fatigue.
NOASSERTION -
cyberjobsactive
Find open cybersecurity jobs with stated salaries from a terminal or from Node, and give MCP clients the CyberJobs.cc tools over stdio.
npm MIT -
hookcraftgithub.com/cognis-digital/hookcraftupdated this year
Generates ready-to-run Frida instrumentation scripts from a YAML intent (e.g. 'bypass SSL pinning', 'dump crypto keys') and verifies they attach to a target process.
NOASSERTION -
Deterministic 6-phase security audit CLI, MCP server, and VS Code extension (1:1:1 parity, *os.Root confinement, SARIF 2.1.0, GHSA advisories)
MIT -
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 -
🛡️ Production-grade Model Context Protocol (MCP) Server for Autonomous AI Security Bug Hunting, Persistent Pentest Memory, Dynamic Checklists, Secret Redaction, and Exploit PoC Generation.
MIT ★ 1 -
aicaudit — AI-powered code audit for Python: taint-path static analysis + evidence-grounded AI verdicts. Every result ships with a machine-checkable source-to-sink path.
MIT -
MCP server for DefectDojo OSS with capability parity to DefectDojo Pro's built-in MCP, plus a deterministic analytics superset. Uses the caller's own API token, so DefectDojo's permissions decide what the model sees.
AGPL-3.0 ★ 2 -
Firebreakgithub.com/synthet1cc/Firebreakupdated this year
Security MCP server that turns your AI into a penetration tester. 20 tools, 100 best practice guides, 47 vulnerability patterns. Connect to Claude, Cursor, or any MCP client.
AGPL-3.0 ★ 5 -
Open source attack-path engine for AWS and Kubernetes: correlates your scanners into one graph and blocks the pull request that opens a route to your data.
Apache-2.0 ★ 9 -
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 -
Burp Suite extension that gives AI agents hands: an MCP server with 160+ Burp operations, plus the Turbo scripting engine for single-packet races, HTTP/2 and HTTP/3.
AGPL-3.0 ★ 2 -
Know which security findings to fix first, across the scanners you already run. SAST, SCA, secrets, IaC and containers, every finding ranked by exposure, criticality, exploitability and, for Go, reachability.
Apache-2.0 ★ 29 -
Find and govern AI attack surfaces in application code, at PR time and inside your AI coding tool (MCP server, Claude Code hook). Free, OSS, runs offline.
MIT ★ 144 -
Agent-neutral security checks before you ship — SAST, secrets, and dependency audit as a merge gate. Find, understand, and fix vulnerabilities in AI- or human-written code. BYO-inference, $0, MIT.
MIT -
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 -
The deterministic attack-surface perception layer for AI security agents. Maps every actionable element of a live, logged-in Chrome page to a unique id; no LLM in the parse (TypeScript port).
npm Apache-2.0 -
Security scanner for MCP servers, as a CLI, GitHub Action and MCP server: tool poisoning, prompt injection, secret leaks and excessive permissions, with SARIF output for CI.
npm Apache-2.0 -
Security scanner for MCP servers, as a CLI, a GitHub Action and an MCP server: tool poisoning, shadowing, excessive permissions, leaked secrets and transport flaws, with SARIF output for CI.
npm Apache-2.0 -
Compiler-grade multi-file security, business-logic & concurrency verifier in Rust. Traces cross-file taint via an O(V+E) Guard-Set Lattice (TS/JS/Go/Python/Rust), proves exploits in a Linux Bubblewrap sandbox, and exposes a stdio MCP server.
Apache-2.0 -
MCPGoatgithub.com/SabyasachiDhal/MCPGoatupdated this year
Deliberately vulnerable MCP server (aka MCP Goat) for security training — 26 challenges across 4 difficulty levels (incl. a secure reference), a victim-agent harness, and one-command Docker deploy. Practice penetration testing against the Model Context Protocol.
MIT ★ 12 -
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.
Apache-2.0 ★ 3 -
tcpkgithub.com/V33RU/tcpkactive
Thick client penetration testing and MSIX security audit toolkit for Windows. Audits .NET, Electron and native binaries: static and runtime checks, IL-verified findings, computed CVSS v4.0, CWE/ATT&CK mapping, SBOM, HTML/Excel reports. PowerShell engine, GUI, MCP server and agentic AI triage.
MIT ★ 24 -
Find the security holes your AI left behind. Zero-config scanner for apps built with Cursor, Claude Code, Lovable & Copilot: leaked keys, open Supabase/Firebase data, missing auth, SQL injection and more. Every finding comes with a fix prompt for your AI editor. CLI + MCP server
MIT ★ 2 -
AI-powered secret scanner for code and git history. Finds leaked API keys, tokens and credentials with near-zero false positives by pairing Rényi entropy detection with LLM adjudication. Runs as a CLI, pre-commit hook, GitHub Action, MCP server or Claude Code hook. Single Go binary, MIT licensed.
MIT ★ 11 -
Agentic security CLI that finds reachable vulnerabilities, writes the fix, and attacks its own patch in an isolated Nebius sandbox. A patch is certified only when the live exploit fails. Powered by NVIDIA Nemotron on Nebius Token Factory. Works as a CI gate and MCP server.
MIT ★ 1 -
MCP server that extends the official GitLab MCP with security, compliance and GitLab Duo tools: vulnerability triage and bulk actions, security policies, compliance violations, SBOM, scanner coverage, Duo usage, seats and credits, and AI governance. One Go binary with a built-in installer for Claude Code and Cursor, and a read-only mode.
MIT