Protect Mcp Setup

This hooks into Claude Code's PreToolUse and PostToolUse events to gate every tool call behind Cedar policies and generate Ed25519-signed receipts that anyone can verify offline. It's designed for situations where you need a cryptographic audit trail, like letting an agent run unattended in a regulated environment or proving to an auditor exactly what decisions were made without them trusting your logs. The receipts are hash-chained and follow RFC 8032, so tampering breaks the chain. If you're just experimenting or working solo, this is overkill. If you're building agent workflows that touch money, PII, or compliance-sensitive operations, the signed evidence and policy enforcement close real gaps that session logs don't.

skills.sh installs: 6.3K
GitHub stars: 42.4K
last updated: Aug 21, 2026

View on GitHub

Install

$ npx -y skills add wshobson/agents --skill protect-mcp-setup --agent claude-code

Installs into .claude/skills of the current project.

Files

protect-mcp — Policy Enforcement + Signed Receipts

Cryptographic governance for every Claude Code tool call. Each invocation is evaluated against a Cedar policy and produces an Ed25519-signed receipt that anyone can verify offline.

Overview

Claude Code runs powerful tools: Bash, Edit, Write, WebFetch. By default there is no audit trail, no policy enforcement, and no way to prove what was decided after the fact. protect-mcp closes all three gaps:

Cedar policies (AWS's open authorization engine) evaluate every tool call before execution. Cedar deny is authoritative.
Ed25519 receipts record the name of each tool that ran, signed with your key.
Offline verification via npx @veritasacta/verify. No server, no account, no trust in the operator.