This release adds 4 notable features for engineering teams evaluating rollout.
Published 5mo
MCP Security & Auth
✓ No known CVEs patched
✓ No known CVEs patched in this version
Topics
agent-security
ai-agent-security
ai-security
claude-code
codex
cursor
+14 more
hallucination-detection
llm-security
mcp
mcp-security
mcp-server
openclaw
owasp
package-hallucination
prompt-injection
static-analysis
security
supply-chain-security
vulnerability-scanning
windsurf
Summary
AI summaryInitial open source release of the Agent Security Scanner MCP server.
Full changelog
agent-security-scanner-mcp v2.0.4
🎉 Initial open source release!
Security scanner MCP server for AI coding agents, providing real-time protection against:
Features
- Prompt Injection Firewall - 56 attack patterns detecting exfiltration, backdoors, and jailbreaks
- Package Hallucination Detection - 4.3M+ packages across 7 ecosystems (npm, PyPI, RubyGems, crates.io, Dart, Perl, Raku)
- Vulnerability Scanner - 359 Semgrep-aligned rules with auto-fix templates
- AST-based Analysis - Optional tree-sitter support for enhanced detection
Supported Clients
Claude Code, Cursor, Windsurf, Cline, Kilo Code, OpenCode, Cody, Zed, and any MCP-compatible client.
Quick Start
npm install -g agent-security-scanner-mcp
npx agent-security-scanner-mcp init claude-code
See README for full documentation.
Weekly OSS security release digest.
The CVE patches and breaking changes that affected production tools this week. One email, every Sunday.
No spam, unsubscribe anytime.
Share this release
About Agent Security Scanner Mcp
All releases →Related context
Related tools
Beta — feedback welcome: [email protected]