mcp-defense

Community

Secure MCP tools with pinned-hash playbooks.

Authorbrucebanner010198-commits
Version1.0.0
Installs0

System Documentation

What problem does it solve?

MCP-specific threat playbook helps governance of MCP tool adoption by pinning descriptions, detecting dangerous content, and enforcing ADR-based approvals.

Core Features & Use Cases

  • Pinning and drift-detection: hash-pin MCP tool descriptions and input schemas to prevent drift and unauthorized changes.
  • Threat-instrumentation checks: scan for instruction-like content in tool manifests and assess for over-permission scenarios.
  • Governance & ADRs: generate adoption ADRs and enforce gated registration via secrets vaults.
  • Runtime safeguards: apply pre-call checks and envelope-wrapped tool metadata to prevent data leakage and injection.

Quick Start

Register a new MCP server and run this skill to validate tool descriptions against the hash registry and generate an ADR.

Dependency Matrix

Required Modules

None required

Components

Standard package

💻 Claude Code Installation

Recommended: Let Claude install automatically. Simply copy and paste the text below to Claude Code.

Please help me install this Skill:
Name: mcp-defense
Download link: https://github.com/brucebanner010198-commits/DevSecOps-Agency/archive/main.zip#mcp-defense

Please download this .zip file, extract it, and install it in the .claude/skills/ directory.
View Source Repository

Agent Skills Search Helper

Install a tiny helper to your Agent, search and equip skill from 471,000+ vetted skills library on demand.