io.github.andysalvo/supership-scan
Predeploy security scanner. 80+ patterns. Runs locally. Optional x402 attestation.
Verdict not yet evaluated for this tool. The hybrid eval runs adversarial cases first; coverage rolls out as the corpus expands. Until a verdict is recorded, an agent should treat this tool as not-yet-cleared and fall back to its own checks. Method: hybrid eval, four-state verdict, honest limits.
{
"mcpServers": {
"supership-scan": {
"command": "npx",
"args": [
"-y",
"supership-scan"
],
"env": {
"SUPERSHIP_URL": "<supership_url>"
}
}
}
}{
"mcpServers": {
"supership-scan": {
"command": "npx",
"args": [
"-y",
"supership-scan"
],
"env": {
"SUPERSHIP_URL": "<supership_url>"
}
}
}
}npx -y supership-scanSUPERSHIP_URLURL of the supership attestation server (optional, defaults to supership.crestsystems.ai)
Security tools for AI agents: scan MCP servers, validate HDP delegation chains, audit releases.
Provide AI-powered real-time analysis and intelligence on NPM packages, including security, depend…
Zenable cleans up sloppy AI code and prevents vulnerabilities with deterministic guardrails