Security●●Solid
MCP-scan – Security scanner for MCP server configs
First security scanner for MCP configs as the protocol gains adoption.
Niche GemShip It
AbanoubRodolf
102mo ago
Back to browse
GitHub Repository
Security scanner for MCP server configurations. Detects secrets, CVEs, permission issues, and exfiltration vectors across 10 AI tool clients.
23 starsTypeScript
MCP-scan – security scanner for MCP server configs
by AbanoubRodolf·Mar 24, 2026·1 point·0 comments
AI Analysis
●●SolidSolve My ProblemShip It
Catches typosquatting and leaked secrets in MCP configs before deployment.
Strengths
- •Detects 43+ API key formats directly in env vars and config args.
- •Typosquatting scanner catches homoglyphs and character swaps in package names.
- •Works as both CLI tool and importable library for CI integration.
Weaknesses
- •npm-only limits adoption; no Python or Rust version for non-JS ecosystems.
- •MCP ecosystem is still nascent — may be premature for most teams.
Category
Target Audience
Developers using MCP servers in Cursor, VS Code, or other AI tooling
Similar To
Socket.dev · npm audit · Snyk
Similar Projects
Security●●Solid
MCP-gateway-scan read-only scanner for MCP production-readiness
Seven-dimension security scoring catches fail-open errors before your MCP gateway hits production.
Niche GemSolve My Problem
willianpinho
204d ago
Security●●Solid
mcpguard – security scanner and firewall for MCP servers
OWASP MCP Top 10 scanner and proxy firewall for AI agent tool calls.
Niche GemSolve My ProblemShip It
GTprojects
2013d ago
Security●●●Banger
MCP-fence – MCP firewall I built and tried to break (6 audit rounds)
Bidirectional scanning catches response-side attacks when 28 other MCP tools only check requests.
Big BrainSolve My Problem
yjcho9317
112mo ago
Security●●Solid
Mcpsec-A multi-agent SEC gate for MCP toolchains (scan →harden →rescan)
MCP-specific security scanning with LLM-powered attack simulation, but assumes MCP adoption maturity that doesn't exist yet.
Big BrainBold Bet
Yuvraj_exe
103mo ago
Security●●●Banger
We scanned 500 ClawHub skills for security risks – 10% were dangerous
19-pattern MCP tool security scanner filling a real gap in agent ecosystem governance.
Solve My ProblemBig Brain
yusufjacobs
313mo ago