広告掲載
MCP.so
ログイン
P

Prompt Injection Shield MCP Server

@aniketkarne

リポジトリ

基本情報

カテゴリ

その他

トランスポート

stdio

作者

aniketkarne

投稿者

Aniket Karne

Prompt Injection Shield MCP Server について

概要はまだありません

Prompt Injection Shield MCP Server の設定

以下の設定を使って、このサーバーを MCP 対応クライアントに追加してください。

{
  "mcpServers": {
    "PromptInjectionShield": {
      "command": "docker",
      "args": [
        "build",
        "-t",
        "shield-mcp",
        "."
      ]
    }
  }
}

Prompt Injection Shield MCP Server 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 Prompt Injection Shield?

Prompt Injection Shield is a local-first, zero-cost MCP server that detects malicious prompt injection and jailbreak attempts in user input. It acts as a security gateway that integrates with LLM workflows (such as Claude Desktop) to pre-screen prompts before they reach the model, keeping all data on the user’s machine.

How to use Prompt Injection Shield?

Install from source (pip install .) or via Docker. Run the server with python -m shield_mcp.server, then configure it as an MCP server in your client (e.g., add to claude_desktop_config.json with command python and args ["-m", "shield_mcp.server"]). The server exposes a single tool called analyze_prompt that accepts a prompt string and returns is_injection, risk_score, and category. You can optionally customize the risk threshold and log directory by creating a shield_config.json file.

Key features of Prompt Injection Shield

  • Local detection engine, no external API calls.
  • Three-tiered detection: heuristics, semantic ML model, and structural check.
  • Privacy-first: prompt text never leaves the machine.
  • Zero-cost security checks.
  • Integrates natively with Claude Desktop and any MCP‑compatible client.

Use cases of Prompt Injection Shield

  • Wrap a chatbot or RAG system to reject malicious prompts before they reach the main LLM.
  • Protect internal tools (code executors, database agents) from injected instructions in data context.
  • Red‑team own applications by using the risk_score to evaluate jailbreak attempts.
  • Pre‑screen any user input in an MCP‑enabled workflow without sending data to a third‑party API.

よくある質問

1

Does Prompt Injection Shield require an internet connection for detection?

No. The entire detection pipeline runs locally; no external API calls are made during analysis.

2

How does the detection work?

It uses three layers: Level 1 heuristics (regex) for known jailbreak patterns, Level 2 semantic analysis with a local DeBERTa model (`protectai/deberta-v3-base-prompt-injection-v2`), and Level 3 structural checks for obfuscation (Base64, Hex, high entropy strings).

3

Can I adjust the detection sensitivity?

Yes. Create a `shield_config.json` in the working directory and set `“risk_threshold”` (default 0.8) to control when a prompt is flagged as injection.

4

Where are logs stored?

Logs are saved by default in `~/.shield-mcp/logs`; you can change the directory using the `“log_dir”` key in `shield_config.json`.

5

What transport does the server use?

The server is invoked via a command (e.g., `python -m shield_mcp.server`) and communicates over MCP’s standard input/output transport (stdio).

コメント

「その他」の他のコンテンツ

Yuppsy

Yuppsy MCP: build and publish real estate websites from your AI assistant. Yuppsy lets your AI assistant create live websites for real estate agents and individual property listings. You don't need a designer or any code

Codelf

unbug

A search tool helps dev to solve the naming things problem.

14.2K

Blender

ahujasid

Open-source MCP to use Blender with any LLM

23.6K

Handl

Handl speaks the Model Context Protocol. Your whole billing operation — projects, invoices, clients, reports, approvals — as tools any AI assistant can call, inside your autonomy rules.

The Living Bread

The Living Bread

A free remote MCP server for The Living Bread. Bible passages read word for word from a stored public domain text with an evidence label, keyword search and cross references, real churches, gatherings and prayer groups w

広告掲載