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.
-
ai-scanner-mcpgithub.com/aakashbhardwaj27/ai-scanner-mcpupdated this year
MCP server for ai-scanner — scan codebases for LLM usage, AI frameworks, and exposed secrets
npm MIT -
leak-secure-mcpgithub.com/cbuntingde/leak-secure-mcpupdated this year
MCP server for Leak Secure - Enterprise GitHub security scanner detecting 35+ types of secrets
npm MIT -
pledgeguardgithub.com/pledgeandgrow/pledgeguardupdated this year
Rust-native secret scanner with MCP server, AST refinement, and WASM plugins
MIT ★ 3 -
visgithub.com/visulima/visactive
Rust-backed Visulima tooling: vis task runner, MCP server, secret scanner, and terminal UI
npm MIT ★ 1 -
codeguard-mcpstale
Real-time AI code security scanner - MCP Server for detecting vulnerabilities, secrets, and compliance issues
npm MIT -
MCP-native secret scanner in one fast Rust binary: engine, CLI, and MCP server. Finds API keys and secrets, skips known-public fixtures, verifies live keys with a real provider call, and applies env-var rewrites. Privacy invariant: the raw secret never leaves disk.
cargo MIT ★ 4 -
A fast workspace auditor, safe artifact cleaner (.venv, node_modules), and security secret scanner exposed via Model Context Protocol (MCP) and Typer CLI.
-
Secret scanner for Web3, cloud and SaaS: 37 detectors + gitleaks-rules import, git-history aware, CVE sweep mode, org/member sweeps, pre-commit hook, MCP server for AI remediation. FP-hardened against real sweeps. TypeScript, 257 tests.
MIT -
probegithub.com/SatishoBananamoto/probeupdated this year
MCP server security scanner — find plaintext secrets, injection vulnerabilities, and missing auth in your MCP configurations
MIT -
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 -
Argus — open-source security scanner (SAST, secrets, malware heuristics, SARIF, MCP). YAML rules welcome — good first issues.
go MIT ★ 10 -
Python dead code, security and secrets scanner with a pull-request gate; narrower checks for TypeScript, Java and more.
pypi Apache-2.0 -
MCP Server Secret Injector (envFile / AES-256-GCM Vault), Tool-Poisoning Scanner & Real-Time stdio JSON-RPC 2.0 Firewall.
MIT ★ 1 -
MCP server that checks a working copy and a customer's proven site: vulnerable packages, secrets, insecure config and code, TLS, headers, exposure and open services, each finding mapped to ENS and NIS2. Native AOT, scanners run in Nomad.
MIT -
reposcan-mcpgithub.com/marilynceo/reposcan-mcpupdated this year
GitHub repository scanner for AI agents u2014 analyze structure, code quality, contributors, dependencies, and detect secrets.
-
secretsweepgithub.com/cognis-digital/secretsweepupdated this year
Repo secret scanner + auto-rotator across providers
NOASSERTION -
revxl-devtoolsgithub.com/johnmives/revxl-devtoolsupdated this year
17 developer tools for AI agents. JSON, JWT, regex, cron, secrets scanner. Free core + Pro ($7).
npm MIT -
Castov in your terminal: Model Context Protocol (MCP) server for Claude & Cursor, EADDRINUSE port killer, cryptographic .env secret generator, IPv4 CIDR subnet calculator, local secret scanner, terminal error healer, .cursorrules generator, Unix timestamp
npm MIT -
Gadriel AI Security Harness for Claude Code — local SAST, SCA/SBOM, secrets, container, config & OWASP LLM security scanner via MCP.
Apache-2.0 -
Gadriel AI Security Harness for VS Code — local SAST, SCA/SBOM, secrets, container, config & OWASP LLM security scanner and MCP server.
npm Apache-2.0 -
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 -
shieldbot-mcpgithub.com/balasriharsha/shieldbotupdated this year
AI-powered security code review MCP server for Claude Code — combines CodeQL, Semgrep (5,000+ rules), bandit, detect-secrets, Dependabot CLI, osv-scanner, Trivy (Docker image scanning), pip-audit, and npm-audit
pypi MIT -
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.
go Apache-2.0 ★ 29 -
Security scanner for MCP (Model Context Protocol) servers. Detect prompt injection, secrets leaks, supply chain attacks, and vulnerabilities in MCP servers. CLI + MCP server mode.
npm MIT ★ 2 -
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 -
@cybrium-ai/mcp-servergithub.com/cybrium-ai/mcp-serverupdated this year
MCP server for AI security + AI governance + AI inventory + code security. Lets Claude, Cursor, Windsurf, Cline invoke cyscan (SAST/SCA/secrets — 1,815 rules / 75+ languages), cyweb (web vulnerability scanner), cyprobe (network discovery), cyradar (discov
npm Apache-2.0 -
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.
go MIT ★ 11 -
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 -
Open source input firewall for AI agents, beta. A local scanner checks text, code, PDFs, images, QR codes, audio and video with 1,565 patterns across 117 categories and reports findings and incomplete scans. A Claude Code hook blocks secret material in tool calls and the paths and hosts your policy lists before tools run.
pypi MIT ★ 11 -
security-scanner-mcpgithub.com/ongjin/security-scanner-mcpupdated this year
MCP server that scans AI-generated code for security vulnerabilities (OWASP Top 10, hardcoded secrets, SQL injection, XSS)
npm MIT -
MCP server for comprehensive security scanning of code repositories
npm MIT -
mcp-secrets-guardgithub.com/chiragborse1/mcp-guardupdated this year
Scan projects for AI and MCP-related secrets before they leak.
pypi MIT -
Premium MCP server that scans projects for dependency issues, secrets, license conflicts, code quality problems, and git health. Returns a 0-100 health score with actionable fix suggestions.
npm MIT -
mcp-semgrep-scannergithub.com/archimedes-market/mcp-semgrep-scannerupdated this year
Run Semgrep static analysis from an AI agent. OWASP top 10, secrets detection, custom rule packs. Baseline scanning to focus only on newly-introduced findings. Built for production-grade security review workflows.
MIT -
catarina-secretsactive
Find leaked API keys in your code and git history, and keep secrets in an encrypted vault your apps and AI agents use without seeing them.
npm MIT -
secscan-mcpgithub.com/openjkai/secscan_mcpupdated this year
MCP server for codebase security scanning (secrets, SAST, SCA, IaC)
pypi MIT -
Local-first developer security scanner with TUI, localhost web UI, and MCP server
npm MIT -
aigategithub.com/joseramos/aigateupdated this year
AI Secret Hygiene — MCP server, proxy, and hooks that catch and remediate hardcoded secrets in AI-generated code
pypi MIT -
MCP server for ClassiFinder — secret scanning tools for AI agents
pypi MIT -
MCP server that lets AI coding agents (Claude Code, Cursor, ...) check content for hardcoded secrets before writing it to disk. Local-only.
npm MIT -
AI-powered security scanner for git repos — CLI, MCP, API, Web Dashboard, SDK with Cerebras LLM
npm Apache-2.0 -
MCP.Secrets.Detectorgithub.com/davidCrejenovschi/MCP.Secrets.Detectorupdated this year
AI-powered inline secrets detector for GitHub Pull Requests. Uses multi-agent LLM scanning (Microsoft Agent Framework + GPT) to flag hardcoded API keys, tokens, passwords, and connection strings directly on code lines — then posts line-level review comments automatically.
-
codemind-mcpgithub.com/codemind-ai/codemindupdated this year
MCP Security Guardian — SAST, Secrets, SCA, IaC scanning for AI-powered development
pypi MIT -
Zero-dependency environment security auditor, secret leak detector, and .env.example generator. CLI, MCP server, and GitHub Action.
Apache-2.0 -
—
npm MIT -
Catch CVEs, leaked secrets, and BTP misconfigurations in your MTA/CAP project before you deploy.
MIT -
Zero-dependency MCP server and SDK for deterministic PII and secret scrubbing with reversible LLM tokenization
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 -
llm-maskupdated this year
MCP server + library + CLI for masking sensitive data before sending to LLMs
npm -
mcp-sentinel-scannergithub.com/j420/mcpsentinalupdated this year
MCP server for security scanning — analyze any MCP server against 177 detection rules with AST taint analysis, capability graph, and entropy-based secret detection
npm MIT -
Smart Git Model Context Protocol (MCP) server & CLI for conventional commits, pre-PR security secret audits, and merge conflict resolution.
MIT -
ghostpatchgithub.com/NeuralRays/ghostpatchupdated this year
AI-powered security vulnerability scanner that runs locally via npm with zero infrastructure. 131+ OWASP rules, 15 languages, free AI analysis, MCP server for coding agents.
MIT ★ 3 -
mcp-n8n-security-scannergithub.com/smakarim/mcp-n8n-security-scannerupdated this year
MCP server that statically scans n8n automation workflows for security issues (SAST for n8n): SSRF/IMDS, code injection, unauth webhooks, hardcoded secrets, PII egress. Includes STRIDE threat model.
MIT -
flarehq-mcpgithub.com/myer-2000/flareupdated this year
Flare MCP server: let Claude Code, Cursor or Windsurf scan your running app and repo for leaked secrets, exposed routes and open RLS — and verify whether a leaked key is still live.
npm MIT -
ironwardgithub.com/rayentr/ironwardupdated this year
Security scanning for the vibe coding era — MCP server + CLI + GitHub Action. 9 tools, 665 secret patterns, 27 static rules. Four tools run fully offline, no API key.
npm MIT ★ 2 -
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 -
vexp-cliactive
Local-first context engine for AI coding agents. Pre-indexes your codebase into a dependency graph and feeds any MCP agent only the code that matters, so it stops rediscovering your repo before every change. Fable-5-level results from Opus 5 on SWE-bench
npm UNLICENSED -
web-exposure-mcpgithub.com/Perufitlife/web-exposure-mcpupdated this year
MCP server that points an AI agent at a live URL and confirms publicly-served secret files — exposed .git, .env, JS source maps, backup/SQL dumps, directory listing, dotfiles — by fetching the bytes. Zero deps, read-only.
MIT ★ 1 -
@betterqa/security-mcpgithub.com/better-quality-assurance/security-toolupdated this year
MCP server for AI-powered security scanning - SAST, SCA, DAST, and secrets detection
npm MIT -
MCP server for local security work — secrets, CVEs, Wi‑Fi/ARP/USB, header audits.
MIT