広告掲載
MCP.so
ログイン

Agent Immune MCP Server

@denial-web

リポジトリ

基本情報

カテゴリ

AI とエージェント

トランスポート

stdio

作者

denial-web

投稿者

Hak You

Agent Immune MCP Server について

Adaptive security toolkit for AI agents. Assess inputs for prompt injection, scan outputs for credential/PII leaks, teach new attack patterns to semantic memory, harden prompts with role-lock and sandboxing, and monitor metrics — all locally via MCP. Zero false positives on bench

#security#ai-security#prompt-injection#mcp#llm-security#agent-governance

Agent Immune 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": {
    "agent-immune": {
      "command": "python",
      "args": [
        "-m",
        "agent_immune",
        "serve",
        "--transport",
        "stdio"
      ]
    }
  }
}

Agent Immune MCP Server のツール

5

score text for prompt injection threats

scan output for credentials, PII, and exfiltration

teach new attack patterns to semantic memory

apply role-lock, sandboxing, and output guards

observability snapshot (counts, latency)

概要

What is Agent Immune?

Agent Immune is an adaptive security toolkit for AI agents that runs locally via the Model Context Protocol (MCP). It provides tools to assess inputs and outputs for threats, learn new attack patterns, harden prompts, and expose observability metrics, targeting developers building secure AI agent workflows.

How to use Agent Immune?

Install it with pip install 'agent-immune[mcp]' and serve it via python -m agent_immune serve --transport stdio. Once running, an MCP host can invoke its five tools: assess_input, assess_output, learn_threat, harden_prompt, and get_metrics.

Key features of Agent Immune

  • Zero false positives on benchmark evaluations.
  • 179 automated tests with 94% code coverage.
  • Semantic memory catches rephrased attacks that bypass regex.
  • Provides prompt hardening via role-lock, sandboxing, and output guards.
  • Observability snapshot through get_metrics tool.
  • Licensed under Apache-2.0.

Use cases of Agent Immune

  • Detect prompt injection threats in user-supplied text before it reaches the AI agent.
  • Scan agent outputs for credentials, PII, and data exfiltration.
  • Teach the system new attack patterns on the fly to adapt to emerging threats.
  • Harden agent prompts with role-lock and sandboxing guards to prevent misuse.
  • Monitor security metrics and latency through the observability snapshot.

よくある質問

1

What does “zero false positives on benchmarks” mean?

On the benchmarks used in testing, no legitimate inputs were incorrectly flagged as threats, ensuring low friction for normal agent operation.

2

How does Agent Immune differ from simple regex-based filters?

Agent Immune uses semantic memory that can recognize rephrased or novel attack patterns, whereas static regex rules often miss variations and produce false negatives.

3

Is Agent Immune a cloud service?

No. It runs entirely locally via the MCP protocol; no data is sent to external servers unless the user explicitly configures it.

4

What transport does Agent Immune use?

The server is started with `--transport stdio`, so it communicates over standard input/output with the MCP host.

5

What are the runtime dependencies?

The package is installed via pip and requires Python. The `agent-immune[mcp]` extra pulls in MCP dependencies, and the tool operates as a standard Python process.

コメント

「AI とエージェント」の他のコンテンツ

L

Legion MCP

faulkj

MCP-native LLM councils for debates, juries, blind panels, voting, refinement, and custom multi-model deliberation.

1

Poly-Glot AI Workspace

hmoses

1,000+ fully localized prompt templates across 40+ categories. Compare Mode — send the same prompt to up to 9 AI providers (ChatGPT, Claude, Gemini, Grok, Groq, Copilot, Mistral, Perplexity, DuckDuckGo AI) and compare an

superbot

EZO Labs

superbot is your own AI agent: anything you can do on your computer, it can do, fast. Its MCP server gives other agents one tool for errands: fax, calls, texts, Gmail drafts, calendar, web search. Free in your browser, n

WordPress MCP Server

miniOrange

miniOrange WordPress MCP Server turns a WordPress site into a Model Context Protocol server, so AI clients like Claude, ChatGPT, Cursor, Gemini and Windsurf can read and edit the site through chat instead of the admin da

SlopIt

SimbaStack

Instant blogs for AI agents: a publishing CMS with no dashboard. One signup call returns a blog, an API key and a live URL; then publish markdown posts and get public URLs back.

広告掲載