io.github.sparkvibe-io/GuardianShield
Quality Score
83
/100
AI security layer: code scanning, PII detection, prompt injection, secrets, CVEs
§01 Install
Claude Desktop (uvx)
{
"mcpServers": {
"GuardianShield": {
"command": "uvx",
"args": [
"guardianshield"
],
"env": {
"GUARDIANSHIELD_PROFILE": "<guardianshield_profile>",
"GUARDIANSHIELD_AUDIT_PATH": "<guardianshield_audit_path>",
"GUARDIANSHIELD_DEBUG": "<guardianshield_debug>"
}
}
}
}§02 Environment variables
GUARDIANSHIELD_PROFILEDefault safety profile (general, education, healthcare, finance, children)
GUARDIANSHIELD_AUDIT_PATHPath to the SQLite audit database
GUARDIANSHIELD_DEBUGSet to 1 for debug logging
§03 MCP Quality Score · methodology
freshness
23
completeness
10
installability
25
documentation
15
stability
10
§04 Alternatives in Security
Helixar Security
ai.helixar/mcp
Security tools for AI agents: scan MCP servers, validate HDP delegation chains, audit releases.
ai.smithery/Nekzus-npm-sentinel-mcp
ai.smithery/Nekzus-npm-sentinel-mcp
Provide AI-powered real-time analysis and intelligence on NPM packages, including security, depend…
app.zenable/zenable
app.zenable/zenable
Zenable cleans up sloppy AI code and prevents vulnerabilities with deterministic guardrails