What does Security Audit Tool scan?
It scans npm package dependencies for known security vulnerabilities using the remote npm registry.
@qianniuspace
Basic information
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.
Add this server to your MCP-compatible client using the configuration below.
{
"mcpServers": {
"mcp-security-audit": {
"command": "npx",
"args": [
"-y",
"@smithery/cli",
"install",
"@qianniuspace/mcp-security-audit",
"--client",
"claude"
]
}
}
}Tool list not available yet
This listing does not currently have a tool list to display. This does not mean the server has no tools; check its documentation for supported capabilities.
Fetch the live tool list by running this server in a temporary sandbox using the button above.
Security Audit Tool is an MCP (Model Context Protocol) server that audits npm package dependencies for security vulnerabilities. It integrates with the remote npm registry to perform real-time security checks and is designed for developers using MCP-compatible clients like Cline or Cursor.
You can install Security Audit Tool via Smithery (npx -y @smithery/cli install @qianniuspace/mcp-security-audit --client claude) or by adding an MCP configuration to your client. For NPX, add a JSON entry with command npx and args ["-y", "mcp-security-audit"]. Alternatively, download the source, build, and point to the built index.js.
It scans npm package dependencies for known security vulnerabilities using the remote npm registry.
It is compatible with npm, pnpm, and yarn.
Reports include severity level, CVE references, CVSS score, fix recommendations, and fixed version if available.
No authentication is mentioned; it uses public npm registry data.
It is configured as an MCP server via the `mcpServers` JSON object in clients like Cline or Cursor.
TestMu AI MCP Server lets developers run, debug, and triage tests through natural language directly from their IDE (Cursor, Claude, GitHub Copilot, and other MCP clients). It exposes five tools — HyperExecute (test orche

Local-first credential broker for MCP. AI coding agents (Claude Code, Cursor, Codex…) call APIs, SSH and databases through scoped presets; secrets stay in your OS keychain and never enter the agent's context.

Most MCP servers hand your agent documentation. This one hands it a renderer. Write a single React Native codebase that ships native AR to phones and VR to headsets, then let your agent validate every prop, check each pl
ZeroBeacon.ai — Collision-proof commerce router for AI agents. 1000 MCP tools: commerce, trust, billing, sovereign ID + everyday tools. LIVE.

Catch intent conflicts before code conflicts. The open-source coordination protocol for coding agents, built above Git.
Comments