mcp-config-poisoning

Official

Assess MCP config poisoning risk in AI IDEs.

AuthorMindgard
Version1.0.0
Installs0

System Documentation

What problem does it solve?

Identifies and assesses MCP configuration poisoning vulnerabilities in AI IDEs, focusing on workspace-level MCP server definitions that could be loaded or trusted without explicit user consent.

Core Features & Use Cases

  • Assess auto-load behavior of MCP configurations from workspace settings.
  • Evaluate approval models, prompt injection risks, and TOCTOU scenarios across multiple IDEs.
  • Build attack-chains from validated primitives to understand risk and remediation steps.

Quick Start

Identify the target IDE's MCP config path and verify whether untrusted workspaces auto-load definitions.

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-config-poisoning
Download link: https://github.com/Mindgard/ai-ide-skills/archive/main.zip#mcp-config-poisoning

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.