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.

A powerful MCP (Model Context Protocol) Server that audits npm package dependencies for security vulnerabilities. Built with remote npm registry integration for real-time security checks.

Claude Code plugin: security news and alerts for the tech your projects actually run on (Composer/npm packages, runtimes, OS packages), from vendor feeds, CISA, OSV and NVD.

Security scanner for AI agent packages — CLI + MCP server

GuardRails by Abscissa: VS Code extension-package security, exact-release evidence, workspace monitoring, and a read-only OAuth MCP server.

FastMCP server that provides comprehensive security analysis for software packages across multiple ecosystems. It integrates seamlessly with Claude Desktop to provide AI-powered security evaluation capabilities.

Legacy MCP security server — superseded by correctover-mcp-gateway for Claude Code, Cursor, Cline and Windsurf.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.

Security MCP server for agentic development. Powers real-time analysis, package scanning, and custom workflows.

MCP server for npm package management — 32 tools for publish, install, audit, search, security & more

MCP security trust layer. Scan packages, inspect repo MCP dependencies, generate Policy Gate setup, install the workflow directly, check exposure, and query abuse data.

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.

Security intelligence API and MCP server in C: CVE, KEV, EPSS, package, domain and IP lookups, and a watch list that reports what changed.

Stop opening 12 tabs to evaluate a library. GitHub repos + npm/PyPI packages + security advisories in one MCP tool call. Zero API keys required.

YuanXinMCP (元信MCP) - the pre-install security scanner for Agent skills, exposed as a stdio MCP server: scan_skill (dir/package -> verdict + findings), generate_badge (audited badge), gate_check (CI gate), get_report (JSON/Markdown). Local offline static s

Open source security for AI agents: an OS-enforced egress wall on macOS, and on Ubuntu 24.04 x86-64 via a separate package; keys only the operator holds; a hash-chained audit record. One command wraps Claude Code, Cursor, Hermes, OpenClaw or Cline on tested config paths. No vendor in the path. Claims trace to the Assurance Matrix.

A production-ready MCP (Model Context Protocol) server for managing Python packages using uv, with enterprise features including security, auditing, and support for both stdio and HTTP transports. The server exposes resources (package lists, dependency trees, project indexing) and tools (install, uninstall, sync) while maintaining learning-focused

Vibe code fast. Ship like an engineer. AI engineering framework packaged as an MCP server that enforces TDD, security scanning, pentesting, secret management, QA audits, and deployment to a securely configured VPS — automated with up to 100× fewer exploration tokens.

npm registry MCP server — package intelligence, security audits, and dependency analysis for AI assistants

Multi-org Sentry MCP server — isolated error monitoring across multiple projects from a single config. Process-level security, handoff package generation.

What changed between two versions of a package: breaking changes, deprecations, security fixes.

openEuler Infra gateway (oed CLI) as local MCP tools: CVE security notices, packages, forum, SIG docs, mailman, search, repos, issues.

npm MCP server: registry tools for package metadata, security audits, dependency trees, and write ops (deprecate, dist-tag, owner).

MCP server: ten web-data tools for AI agents (search, page reading, contacts, tech stack, company profiles, e-mail security, package health) powered by Apify Actors

Drive any Electron app from your AI. MCP server with 93 tools, 4 recipe packages (Slack/Discord/Notion/Linear), security primitives, and a CLI mirror. The testing surface area Tauri structurally cannot match.

Local security check for AI-built apps: leaked keys, open Supabase/Firebase rules, risky packages — then hand fixes to your AI. AI로 만든 앱의 키 노출·접근 규칙·취약 패키지를 로컬에서 검사합니다. 本地检查 AI 生成应用的密钥泄露、开放的访问规则和有风险的依赖包。

Secure Node.js execution sandbox for AI. Allows coding agents & LLMs to dynamically run JavaScript, install NPM packages, and retrieve results, facilitating code generation, testing, and interactive assistance. MCP-compatible.

an AI-native edge MCP controller that packages local device + network services into a single MCP Server for authorized agents. Tool convergence cuts token cost, 5-layer security ensures zero-trust, dual open-source frameworks (ESP32 + plugin engine, MIT) enable AI-constrained code generation. Pure local Rust core, Docker deployment.

Audit your package.json dependencies

Nipmod package intelligence, Codex plugin, MCP workflows and public agent safety tooling.

Evidence-first npm package and project dependency checks for developers, coding agents, and MCP clients before code executes.

Dependency vulnerability and malicious package scanner for AI agents and MCP: check package.json, package-lock.json, requirements.txt, go.mod, Cargo.lock for known CVEs (GHSA, OSV) and malware before npm install. Free MCP server; full advisories via x402

MCP server for supply chain package scanning — detects typosquatting, malicious install scripts, obfuscation, and dependency confusion in npm/PyPI packages. Works with Claude Code, Cline, and any MCP client.

Package & dependency intelligence for AI coding agents. Free npm, PyPI and crates.io health, vulnerability, dependency-graph and download data over MCP; consolidated risk scores paid per-call in USDC via x402.

Stop AI coding agents installing packages that do not exist. MCP server + CLI for detecting hallucinated and slopsquatted npm packages. Zero dependencies.

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.

MCP tool packages (.mcpb) for AI-driven network device ops — firewall REST API toolkits (NSFOCUS / Hillstone / YAXIN / ASG, 490+ tools) + open package format spec. 灵枢 MCP 扩展包生态：防火墙/网络设备运维工具集

The Lazaretto MCP server and npm package: a free lockfile malware check, plus full scans of npm packages, agent skills and MCP servers.

Reduce MCP tool overload with a single Go binary that indexes tools locally and serves search-before-invoke via SQLite

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.

Catch hallucinated and squatted packages before an AI agent installs them. MCP server + CLI, zero dependencies.

Validate OTA update packages end-to-end: signature chains, rollback protection, anti-downgrade counters, and delta-patch integrity.

Ground truth about npm packages for AI coding agents. Catches hallucinated and slopsquatted dependencies before they reach your lockfile.

MCP server that tells an AI agent whether a download URL or install command is a project's official channel, before it is fetched or run. 在 AI agent 下載或安裝之前，判斷網址或安裝指令是否為專案的官方管道。

Let AI coding agents use your secrets without ever seeing them. Encrypted local vault, self-hosted Vaultwarden/Bitwarden, or your team's HashiCorp Vault, OpenBao, Infisical, 1Password, AWS, Google Cloud or Azure secrets; masked output, MCP server, Claude

Standalone npm-package for PT Application Inspector MCP

Scans code changes for leaked secrets and insecure config, with actionable fixes for AI agents. MCP server, docs for the leakrank-guard npm package.

Install gate for AI coding agents: blocks malicious, hallucinated and typosquatted packages (npm, PyPI, crates.io, Go) before Claude Code installs them. Hook + MCP server + CLI.

Is this dependency still maintained? MCP server, CLI and GitHub Action that score npm packages, PyPI packages and GitHub repositories 0-100 for maintenance health, with an A-F grade and a list of risks.

npm install, reimagined for AI agents: an MCP server that vets npm releases against the package's own history before an agent installs them

Deterministic, non-executing evidence and change monitoring for public npm MCP servers. Reports what changed since the version you approved. It never claims a package is safe.

MCP server for PyPI: search packages and audit dependency trees against OSV vulnerability data before an agent suggests them.

Version-accurate library docs and a dependency check for AI coding agents. MCP server, pre-install hook, CLI and GitHub Action that check every package an agent pins (advisories, malware, lookalikes, versions that do not exist) before the install runs. Local, MIT.

Claude에서 토스증권 계좌로 국내·미국 주식을 조회하고 주문하는 MCP 서버 · Toss Securities MCP server for Korean and US stocks

Ground truth about npm and PyPI packages for AI coding agents. Detects hallucinated and slopsquatted dependencies before they get installed.

Stops AI coding assistants from using packages, files, and functions that don't exist. A safety net against hallucinated and slop-squatted names.

Risk signals for a repository or an npm/PyPI package, with evidence. Never runs the target's code.

Check an MCP server before you install it: dated facts from daily initialize/tools/list checks of public MCP servers, MCP Registry declarations, npm/PyPI package state, tool-definition changes and payment terms (x402, MPP, L402). Remote MCP and stdio. No

ScriptProbe MCP server from Compound Labs. Checks an npm package for install scripts, network access and publisher changes before you install it. No key and no signup.

Runs the DeFade MCP stdio server. Thin alias for the `defade` package, which carries the implementation — `npx defade-mcp` and `npx -p defade defade-mcp` are equivalent.

Check messages, npm packages and crypto addresses before acting. The engine behind savesavesavesave.xyz, for scripts and AI agents (library, CLI and MCP server). Read-only, zero dependencies.