mcp-security-governance
CommunitySecure MCP agents from malicious servers.
Authorabhishekmmgn
Version1.0.0
Installs0
System Documentation
What problem does it solve?
MCP agents face risks from dynamic capability changes, tool shadowing, and unsafe actions initiated by untrusted external servers.
Core Features & Use Cases
- Defensive Pinning: Pin tool definitions to trusted versions to prevent runtime changes.
- Allowlisting & Scoped Credentials: Enforce explicit allowlists and constrained credentials for high-risk tasks.
- Threat Mitigation: Detect and reject tool name collisions and enforce policy boundaries during agent-server interactions.
Quick Start
Configure a trusted server, enable tool pinning, and run a connection test to ensure only approved tools are exposed to the MCP agent.
Dependency Matrix
Required Modules
None requiredComponents
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-security-governance Download link: https://github.com/abhishekmmgn/skills/archive/main.zip#mcp-security-governance Please download this .zip file, extract it, and install it in the .claude/skills/ directory.
Agent Skills Search Helper
Install a tiny helper to your Agent, search and equip skill from 223,000+ vetted skills library on demand.