What vulnerabilities are demonstrated?
The project demonstrates prompt injection, tool poisoning, excessive permissions, rug pull attacks, tool shadowing, indirect prompt injection, and token theft.
MCP Security
@Tomby68
基本情報
MCP Security について
An exploration of common MCP server vulnerabilities, along with a deep dive into MCP server prompt injection (+demonstrations for each!).
MCP Security の設定
MCP Security のツール
ツール一覧はまだありません
この掲載には表示できるツール一覧がまだありません。サーバーにツールがないという意味ではありません。対応機能はプロジェクトのドキュメントをご確認ください。
ツールは README から自動的に抽出されます。メンテナーは ## Tools という見出しの下に記載することで、このタブに反映できます。
概要
What is Model Context Protocol (MCP) Security?
This project focuses on MCP client security, demonstrating how MCP servers could expose clients to vulnerabilities. It implements example vulnerabilities and proposed client architectures such as a Dual LLM pattern and a tool‑poisoning‑based logger.
How to use Model Context Protocol (MCP) Security?
Install Python packages with pip install -r requirements.txt and set your OpenAI API key in a .env file. Then run one of the provided MCP servers (e.g., python DVMCPS-Demos/indirect-prompt-injection/server.py) and launch the corresponding client with an optional prompt (-p). For local testing, install Ollama and pull llama3.2 to use the local client.
Key features of Model Context Protocol (MCP) Security
- Demonstrates 7 example MCP vulnerabilities via the Damn Vulnerable MCP Server.
- Implements a Dual LLM architecture to mitigate indirect prompt injection.
- Provides a tool‑poisoning‑based logging approach for better observability.
- Combines Dual LLM and logging into a single client.
- Includes both OpenAI‑powered and local (Ollama) client options.
- Supports optional user‑supplied prompts for each demo.
Use cases of Model Context Protocol (MCP) Security
- Security researchers analyzing MCP client vulnerabilities.
- Developers building MCP clients and testing their resilience to prompt injection.
- Teams adding logging and auditing to MCP agent tool calls.
よくある質問
How does the Dual LLM approach work?
A Controller (MCP client) sends user prompts and tool descriptions to a Privileged LLM, which decides which tools to call. A Quarantined LLM handles tool outputs without calling tools, mitigating indirect injection.
What are the limitations of the Dual LLM design?
It does not prevent standard prompt injection (unsafe user prompts) or tool poisoning attacks (malicious tool descriptions).
What dependencies are required?
Python packages from `requirements.txt`, an OpenAI API key (or Ollama with `llama3.2` for local mode), and the MCP servers included in the project.
How do I run a specific vulnerability demo?
Navigate to its directory, run the server script, then run the client script. For example: `python DVMCPS-Demos/indirect-prompt-injection/server.py` and `python DVMCPS-Demos/indirect-prompt-injection/client.py [-p PROMPT]`.
「開発者ツール」の他のコンテンツ
Mobbin
MobbinMobbin MCP connects your AI agents to 600,000+ real product screens, so what they build starts with what already works.
Nebelus
NebelusNebelus is an enterprise agentic-AI platform for regulated industries. This MCP server exposes the Nebelus Construction API: ~48 tools that give an MCP client full agent build parity — create/update/probe agents, edit ag
Modelglass
ModelglassModelglass turns "which model should I use?" into a lookup instead of a guess. Seven tools give your agent live pricing across image, language, video, and audio models. Sourced and versioned, not scraped once and forgott
1
Foremerge
naw103Catch intent conflicts before code conflicts. The open-source coordination protocol for coding agents, built above Git.
50
Mcp-Warden
ermolukLocal-first credential broker for MCP. AI coding agents (Claude Code, Cursor, Codex…) call APIs, SSH and databases through scoped presets; secrets stay in your OS keychain and never enter the agent's context.
4
コメント