MCP Hub
Back to servers

project-shield

Security scanner for MCP servers and AI-generated code. Detects leaked API keys, PII, prompt injection, and MCP misconfigs with A-F security grades.

Updated
Feb 18, 2026

Project Shield

Security scanner for MCP servers and AI-generated code.

One command to security-grade your MCP server.

What it detects

LayerWhatHow
🔑 SecretsAPI keys, tokens, credentialsRegex + entropy + context analysis
👤 PIIEmail, phone, SSNPattern matching + checksum validation
💉 Prompt InjectionAttacks in MCP tool descriptionsHeuristic + pattern detection
🛡️ MCP MisconfigMissing auth, open permissions, no loggingConfig rule engine

Security Grades

GradeMeaning
AExcellent — ship with confidence
BGood — minor improvements suggested
CClean — some issues to address
DWarning — fix before deploy
EWarning — significant issues found
FLocked — deployment blocked until fixed

Quick Start

npx project-shield scan .

MCP Server Config

{
  "mcpServers": {
    "project-shield": {
      "command": "npx",
      "args": ["-y", "project-shield", "scan", "."]
    }
  }
}

Features

  • 275+ detection rules across 4 security layers
  • A-F grading system with automatic deploy lock on F
  • Evidence Packs — SHA-256 hashed, tamper-proof scan results
  • Fix-it guides — actionable remediation for every finding
  • Badge system — verifiable security badges for your projects

Pricing

PlanPriceScansFeatures
Free$05/monthBasic reporting
Pro$29/month50/monthPDF reports, Evidence Packs
Team$99/monthUnlimited (5 users)CI/CD integration
Enterprise$299+/monthCustomSSO, audit trails

Links

License

Proprietary — see shield.codemeant.dev for terms.

Reviews

No reviews yet

Sign in to write a review