Parses composer.json manifests to extract Packagist dependency trees for vulnerability scanning against OSV.dev.
Exports scan findings in SARIF format compatible with GitHub Code Scanning for CI/CD integration.
Scans JavaScript dependencies from package.json and yarn.lock against npm packages for known vulnerabilities via OSV.dev.
Scans PHP dependencies from composer.json against Packagist packages for known vulnerabilities via OSV.dev.
Scans Python dependencies from requirements.txt against PyPI packages for known vulnerabilities via OSV.dev.
Backs audit logging and scan history with SQLite, enabling querying of past findings and filtering.
Detects hardcoded Stripe API keys and secrets in source code.
Parses yarn.lock manifests to extract npm dependency trees for vulnerability scanning against OSV.dev.
Click on "Install Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type @ followed by the MCP server name and your instructions, e.g., "@GuardianShield scan this code for vulnerabilities"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
Universal AI security layer — an open-source MCP server for code scanning, PII detection, prompt injection defense, secret detection, dependency auditing, and audit logging.
Zero dependencies · 27 MCP tools · 5 safety profiles · 108+ detection patterns
Code Vulnerability Scanning — SQL injection, XSS, command injection, path traversal with CWE IDs and auto-fix remediation
Cross-line Data Flow Analysis — DeepEngine tracks tainted data from sources to sinks across multiple lines using AST-based taint propagation (Python) and regex (JS/TS)
Dependency Security — Version-aware CVE matching against OSV.dev for PyPI, npm, Go, and Packagist ecosystems
Manifest Parsing — Auto-detects 11 formats (requirements.txt, package.json, yarn.lock, go.mod, composer.json, and more)
Prompt Injection Defense — 9+ detection patterns for instruction override, role hijacking, ChatML injection
PII Detection — Email, SSN, credit card, phone, IP — with automatic redaction in findings
Secret Detection — AWS keys, GitHub tokens, Stripe keys, JWTs, passwords, connection strings
Safety Profiles — 5 built-in profiles (general, education, healthcare, finance, children)
Audit Logging — SQLite-backed scan history with finding retrieval and filtering
Related MCP server: zentric-protocol-mcp
pip install guardianshield# Register with Claude Code
claude mcp add guardianshield -- guardianshield-mcp
# Or run directly
guardianshield-mcp# Claude Code
claude mcp add guardianshield -- guardianshield-mcp
# VS Code (.vscode/mcp.json)
{"servers": {"guardianshield": {"type": "stdio", "command": "guardianshield-mcp"}}}
# Cursor (.cursor/mcp.json)
{"mcpServers": {"guardianshield": {"command": "guardianshield-mcp"}}}
# Claude Desktop (claude_desktop_config.json)
{"mcpServers": {"guardianshield": {"command": "guardianshield-mcp"}}}Tool | Description |
| Scan source code for vulnerabilities and hardcoded secrets |
| Scan a single file (auto-detects language from extension) |
| Recursively scan a directory with filtering and progress streaming |
| Check user/agent input for prompt injection attempts |
| Check AI output for PII leaks and content violations |
| Detect hardcoded secrets and credentials |
| Scan multiple files in one call |
| Parse unified diff and scan only added lines |
Tool | Description |
| Check packages for known CVEs via OSV.dev (PyPI, npm, Go, Packagist) |
| Sync the local OSV vulnerability database |
| Parse any supported manifest file (11 formats) into dependency objects |
| Scan a directory for manifest files and check all deps for vulnerabilities |
Tool | Description |
| Mark a finding as false positive (flags future matches) |
| List active false positive records with optional filter |
| Remove a false positive record by fingerprint |
Tool | Description |
| List available analysis engines with capabilities |
| Set active analysis engines for code scanning |
Three engines ship built-in: regex (line-by-line pattern matching, enabled by default), deep (cross-line taint tracking), and semantic (structure-aware confidence adjustment).
Tool | Description |
| Export findings as SARIF 2.1.0 JSON for GitHub Code Scanning and CI |
| Save current findings as a baseline for delta scanning |
| Scan code and report only new findings vs. baseline |
| Evaluate findings against severity thresholds (pass/fail/warn) |
| Scan multiple files in one call |
| Parse unified diff and scan only added lines |
Tool | Description |
| Get current safety profile configuration |
| Switch safety profile (general, education, healthcare, finance, children) |
| Test a regex pattern against sample code for custom pattern development |
| Query the security audit log |
| Retrieve past findings with filters |
| Get health, configuration, and OSV cache statistics |
Set environment variables to customize behavior:
Variable | Description | Default |
| Default safety profile |
|
| Path to SQLite audit database |
|
| Enable debug logging ( | disabled |
Full documentation: sparkvibe-io.github.io/GuardianShield
Apache 2.0
Unclaimed servers have limited discoverability.
If you are the server author, to access and configure the admin panel.
Threat modeling, code/cloud/pipeline scanning, shadow-AI discovery, compliance checks and fixes.
Pay-per-call cybersecurity for AI agents: vuln scans, threat intel, compliance, code security.
The WAF for agents. Pattern-based + heuristic firewall scans prompts, RAG documents, tool argume...
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/sparkvibe-io/GuardianShield'
If you have feedback or need assistance with the MCP directory API, please join our Discord server
