Install
$ agentstack add mcp-andreagriffiths11-mcp-config-scan ✓ scanned · ✓ verified, works with Claude Code, Cursor, and more.
Security review
✓ PassedNo issues found. Passed automated security review. · v0.1.0 How review works →
- ✓ Prompt-injection patterns
- ✓ Secret / credential exfiltration
- ✓ Dangerous shell & filesystem operations
- ✓ Untrusted network calls
- ✓ Known-malicious package signatures
What it can access
- ● Network access Used
- ✓ Filesystem access No
- ✓ Shell / process execution No
- ✓ Environment & secrets No
- ✓ Dynamic code execution No
From automated source analysis of v0.1.0. “Used” means the capability is present in the source — more access means more to trust, not that it’s unsafe.
Verified badge
Passed review? Show it. Paste this badge into your README, it links to the public security report.
Reliability & compatibility
Declared compatibility
Compatibility is declared by the source manifest. End-to-end runtime verification is coming, see below.
We're building live execution health for every listing: tool-call success rate, median latency, uptime, and last-checked timestamps, measured, not self-reported. It isn't live yet, so we don't show numbers we can't stand behind.
How agent discovery & health will work →About
MCP Scan - Scanner for MCP Configurations
🔒 Experimental security scanner for Model Context Protocol (MCP) configuration files
> ## ⚠️ IMPORTANT: EXPERIMENTAL SOFTWARE ⚠️ > > THIS IS EDUCATIONAL SOFTWARE FOR DEMONSTRATION PURPOSES ONLY > > - Not for production security decisions > - May produce false positives or miss real vulnerabilities > - For learning about MCP security concepts only > - Always verify findings manually > - Not a replacement for professional security auditing
Features
- Detects exposed API keys, secrets, and cloud credentials
- Finds dangerous filesystem and command injection risks
- Checks for insecure configuration settings
- Colorful console output & structured JSON reports
- Sensitive data masking, report encryption, secure deletion
📊 SwampUp 2025 Talk
Slides and demo materials: ➡️ [SwampUp 2025 Slides & Demo](swampup/README.md)
Installation
Option 1: Download Pre-built Binary
# Linux/macOS
curl -L https://github.com/AndreaGriffiths11/mcp-config-scan/releases/latest/download/mcp-scan -o mcp-scan
chmod +x mcp-scan
# Windows
curl -L https://github.com/AndreaGriffiths11/mcp-config-scan/releases/latest/download/mcp-scan.exe -o mcp-scan.exe
Option 2: Build from Source
git clone https://github.com/AndreaGriffiths11/mcp-config-scan.git
cd mcp-config-scan
go build -o mcp-scan
Option 3: Go Install
go install github.com/AndreaGriffiths11/mcp-config-scan@latest
Usage Examples
./mcp-scan # Scan current directory
./mcp-scan -c config/mcp.json # Scan specific JSON files
./mcp-scan -c config/mcp.yaml # Scan specific YAML files
./mcp-scan -f json -o report.json # Generate JSON report
./mcp-scan demo # Run demo scan
./mcp-scan -v # Verbose output
./mcp-scan -q # Compact output format
Configuration Discovery
Scans config files in:
./mcp.json,./mcp.yaml,./mcp.yml./config/mcp.json,./config/mcp.yaml,./config/mcp.yml~/.mcp/config.json,~/.mcp/config.yaml,~/.mcp/config.yml~/.config/mcp/config.json,~/.config/mcp/config.yaml,~/.config/mcp/config.yml
Security Checks
- Critical: Exposed API keys (OpenAI, Anthropic, Mistral, Cohere, Hugging Face, GitHub, AWS, etc.), cloud credentials, private keys, DB credentials
- High: Dangerous filesystem access, shell injection, insecure network settings
- Medium: Dangerous commands, debug mode, suspicious paths
- Low: Disabled configs, excessive timeouts
Example Output
╔═══════════════════════════════════════════════════════════════╗
║ MCP SCAN v1.0 ║
║ Security Scanner for MCP Configurations ║
║ SwampUP 2025 Edition ║
╚═══════════════════════════════════════════════════════════════╝
✅ demos/secure-config.json - No security issues found
❌ demos/vulnerable-config.json - 12 issues found:
[CRITICAL] Exposed OpenAI API Key detected
[HIGH] Dangerous filesystem access in workingDir
[HIGH] Potential shell injection vector
[MEDIUM] Debug mode enabled
════════════════════════════════════════════════════════════════
📊 SCAN SUMMARY
Configurations scanned: 4
Security issues found: 18 ❌
⚠️ Please review and address the security findings above
════════════════════════════════════════════════════════════════
Demo Configurations
Educational examples in the demos/ directory:
- secure-config.json — Best practices
- vulnerable-config.json — Intentionally unsafe
- mixed-config.json — Secure & risky configs
- development-config.json — Common pitfalls
Building from Source
go mod download
go build -o mcp-scan
Contributing
We welcome contributions! Here's how you can help:
🐛 Report Bugs
- Use GitHub Issues
- Include MCP config samples (redact secrets!)
- Describe expected vs actual behavior
💡 Suggest Features
- New secret patterns to detect
- Additional security checks
- Output format improvements
- Integration ideas
🔧 Code Contributions
- Fork the repository
- Create feature branch:
git checkout -b feature/amazing-detection - Add tests for new security checks
- Ensure all tests pass:
go test ./... - Submit pull request with clear description
📋 Development Setup
git clone https://github.com/AndreaGriffiths11/mcp-config-scan.git
cd mcp-config-scan
go mod download
go build -o mcp-scan
./mcp-scan demo # Test it works with dummy data
See [CONTRIBUTING.md](CONTRIBUTING.md) for detailed guidelines.
License
MIT License — see LICENSE file.
⚠️ Security Disclaimer
> ## CRITICAL: EDUCATIONAL USE ONLY > > MCP Scan is an experimental educational tool and should NEVER be used for: > - Production security decisions > - Compliance reporting > - Security assessments of live systems > - Any situation where accuracy is critical > > This tool may: > - Generate false positives (flag safe configurations as dangerous) > - Miss real security vulnerabilities (false negatives) > - Misinterpret configuration contexts > - Fail to detect novel attack patterns > > Always: > - Verify all findings manually > - Consult security professionals for production systems > - Use established enterprise security tools for real audits > - Understand this is for learning MCP security concepts only
Source & license
This open-source MCP server is cataloged on AgentStack and links to its original source — we do not rehost the code.
- Author: AndreaGriffiths11
- Source: AndreaGriffiths11/mcp-config-scan
- License: MIT
Install and usage instructions live in the source repository linked above.
Reviews
No reviews yet, be the first.
Write a review
Versions
- v0.1.0 Imported from the upstream source.