protect-mcp — independently scanned and version-tracked by SaferSkills.
SaferSkills independently audited protect-mcp (Agent Skill) and scored it 100/100 (green). The audit ran 55 deterministic rules across Security, Supply Chain, Maintenance, Transparency, and Community; it found 0 high-severity and 0 lower-severity findings. The full rule-by-rule trace and per-finding evidence are below. Free, methodology-open.
Findings & checks · 0 flagged
Every scanned point with the score it earned and what moved between them.
First recorded scan — no prior version to compare against.
The primary manifest — the file an agent reads to learn what this artifact does.
Adds two layers to every tool call:
authorization engine AWS uses for IAM. Policies are declarative .cedar files.
If the record is modified after signing, the signature breaks. Anyone can verify offline without trusting the issuer.
# One-time: configure Claude Code hooks
npx [email protected] init-hooks
# Start the hook server (runs on port 9377)
npx [email protected] serve --enforceThis configures Claude Code to POST every tool call event to protect-mcp for policy evaluation and receipt signing. First run auto-generates permissive Cedar policies that you can tighten.
Once running, protect-mcp operates silently. Every tool call:
.protect-mcp-log.jsonl# Verify all receipts in the log
npx @veritasacta/verify .protect-mcp-log.jsonl
# Verify a single receipt
npx @veritasacta/verify receipt.json{
"type": "protectmcp:decision",
"tool_name": "Bash",
"decision": "allow",
"policy_digest": "sha256:a3f8...",
"issued_at": "2026-04-04T12:00:00Z",
"signature": { "alg": "EdDSA", "sig": "..." }
}// Block destructive commands
forbid (
principal,
action == Action::"tool_call",
resource == Tool::"Bash"
) when {
context.input.command like "rm -rf *"
};~30 seconds. Free. No account. Every finding cites a rule and a line of evidence.