agent-security-scanner-mcp vs Modelcontextprotocol Core
agent-security-scanner-mcp and Modelcontextprotocol Core are both security MCP servers. Modelcontextprotocol Core scores higher (94 vs 79 out of 100). Modelcontextprotocol Core has more GitHub stars (14k), and Modelcontextprotocol Core was updated more recently (3 days ago). The table compares them side by side.
| agent-security-scanner-mcp | Modelcontextprotocol Core | |
|---|---|---|
| Score | 79 / 100 | 94 / 100 |
| What it does | Security layer for AI agents: blocks prompt injection, detects fake packages, scans vulnerabilities. | Model Context Protocol for TypeScript — public Zod schemas (spec + OAuth/OpenID) (with updated dependencies) |
| Publisher | Community: sinewaveai | Verified: npm:@depup |
| Grades | Maintenance A, Licence A, Quality B | Maintenance A, Licence A, Quality A |
| npm downloads a week | 203 | 74 |
| Runs | Local | Local |
| Works with | Claude Code, Claude Desktop, Cursor, Codex, Gemini CLI, VS Code, Windsurf | Claude Code, Claude Desktop, Cursor, Codex, Gemini CLI, VS Code, Windsurf |
| GitHub stars | 124 | 13,621 |
| Last commit | 18 Oct 2026 | 20 Oct 2026 |
| Licence | MIT | Apache-2.0 |
| Listed since | 19 Oct 2026 | 20 Oct 2026 |
| Install agent-security-scanner-mcp | Install Modelcontextprotocol Core |
Questions
Is agent-security-scanner-mcp or Modelcontextprotocol Core more popular?
Modelcontextprotocol Core has more GitHub stars: 13,621.
Can I use agent-security-scanner-mcp and Modelcontextprotocol Core together?
Yes. AI assistants can load several MCP servers at once. Install both and the assistant picks the right one for each task.