protect-mcp-setup

Enforce policy control and auditability for Claude Code tool calls.

Updated Apr 5, 2026
One-click install
npx skills add https://github.com/Jhabbig/Habbig --skill protect-mcp-setup-jhabbig
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: protect-mcp-setup
Source: https://github.com/Jhabbig/Habbig/tree/main/.claude/plugins/wshobson/protect-mcp/skills/protect-mcp-setup
Command: npx skills add https://github.com/Jhabbig/Habbig --skill protect-mcp-setup-jhabbig

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This Skill helps teams control and prove how Claude Code tool calls are executed, replacing ad hoc trust with policy checks and tamper-evident receipts.

Core Features & Use Cases

  • Policy enforcement before each tool call so unsafe actions can be blocked automatically.
  • Signed receipts after each tool call so decisions and outputs can be verified offline.
  • Ideal for compliance workflows, regulated environments, and teams that need evidence of agent actions during code changes or automation runs.

Quick Start

Ask Claude Code to set up protect-mcp in your project so every tool call is policy-checked and signed into an audit trail.

Frequently Asked Questions about protect-mcp-setup

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I enforce policy control before Claude Code tool calls?

You enforce policy control by applying Cedar policy evaluation to gate execution for Bash, Edit, Write, and WebFetch actions, automatically blocking unsafe Claude Code tool calls before they run.

How do I generate tamper-evident audit trails for Claude Code actions?

You generate tamper-evident audit trails by creating Ed25519 signed receipts and applying hash chaining after each Claude Code tool call, producing compliance-ready evidence that supports offline verification.

What is offline verification for signed receipts in agent workflows?

Offline verification for signed receipts is the cryptographic validation of Ed25519 signatures and hash chains from agent workflows without network access, proving tool call decisions and outputs remain untampered.

Does Cedar policy evaluation work with Claude Code Bash and Edit actions?

Yes, Cedar policy evaluation works with Claude Code Bash and Edit actions by intercepting those tool calls to check permissions and block non-compliant execution before it happens.

When do I need cryptographic receipts for Claude Code automation?

You need cryptographic receipts for Claude Code automation when operating in regulated environments or compliance workflows that require tamper-evident, offline-verifiable evidence of agent actions during code changes.

Can I use Ed25519 signing and hash chaining for compliance-ready evidence?

Yes, you can use Ed25519 signing and hash chaining to produce compliance-ready evidence, replacing ad hoc trust with cryptographically signed receipts that prove the integrity of each tool invocation.