広告掲載
MCP.so
ログイン

Derisk MCP Server

@derisk-ai

リポジトリ

基本情報

カテゴリ

その他

ライセンス

MIT

トランスポート

stdio

作者

derisk-ai

Derisk MCP Server について

AI-Native Risk Intelligence Systems, OpenDeRisk——Your application system risk intelligent manager provides 7* 24-hour comprehensive and in-depth protection.

#agent#devops#risk-analysis#rl#sre#aigc#llms#mcp-server#ai-sre

Derisk 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": {
    "derisk": {
      "command": "uv",
      "args": [
        "sync",
        "--all-packages",
        "--frozen",
        "\\"
      ]
    }
  }
}

Derisk 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 Derisk?

Derisk (OpenDeRisk) is an AI-native risk intelligence system that acts as an intelligent manager for your application, providing 24/7 comprehensive protection through multi-agent root cause analysis and visualization.

How to use Derisk?

Install via curl -fsSL https://raw.githubusercontent.com/derisk-ai/OpenDerisk/main/install.sh | bash, then configure API keys in ~/.openderisk/configs/derisk-proxy-aliyun.toml and run openderisk-server. Alternatively, clone the source, install dependencies with uv, and start with uv run derisk quickstart. Access the web UI at http://localhost:7777.

Key features of Derisk

  • DeepResearch RCA for root cause analysis from logs, traces, and code
  • Visualized evidence chain for clear diagnostic process
  • Multi-agent collaboration (SRE, Code, Report, Vis, Data agents)
  • Open-source architecture with MIT license
  • Supports flame graph and data analysis modes

Use cases of Derisk

  • AI-SRE: Root cause analysis using the OpenRCA dataset
  • Flame Graph Assistant: Analyze Java/Python flame graphs from applications
  • DataExpert: Conversational analysis of metrics, logs, traces, or Excel data

よくある質問

1

What datasets does Derisk use?

Derisk relies on the OpenRCA dataset (approximately 26GB decompressed) for root cause analysis, with bank and telecom subsets available for download.

2

How do I configure API keys?

Edit `~/.openderisk/configs/derisk-proxy-aliyun.toml` after installation and set your API keys for the proxy (e.g., OpenAI). A web UI also allows model configuration after starting the server.

3

What are the runtime dependencies?

Derisk requires Python and `uv` (package installer). Optional extras include RAG, ChromaDB storage, OSS2 storage, DingTalk channel, and OpenAI proxy support.

4

Is Derisk open source and free to use?

Yes, Derisk is released under the MIT license and is completely open source. The architecture is designed for reuse and extensibility.

5

Where does the data reside?

Datasets are downloaded locally and placed in `pilot/datasets/` under the project directory. No data is sent to external cloud services by default.

コメント

「その他」の他のコンテンツ

P

PickFu MCP

PickFu MCP is a Model Context Protocol (MCP) server that connects AI assistants, developers, marketers, product managers, and AI agents to PickFu's consumer research platform. It enables users to create surveys, conduct

Activepieces

activepieces

AI Agents & MCPs & AI Workflow Automation • (~400 MCP servers for AI agents) • AI Automation / AI Agent with MCPs • AI Workflows & AI Agents • MCPs for AI Agents

23.2K

ICSS

chokcoco

不止于 CSS

20.7K

Volley.sh

Volley

A good sequence diagram can solve almost any communication problem in engineering. Volley lets your agent write them as plain text, with the real request and response payloads on every arrow. It checks its own syntax wi

Klarix Intelligence Engine

Klarix

B2B competitive intelligence, live sales battlecards, 5-axis ICP prospect fit scoring, and tech stack teardowns over MCP and REST with cited public-web evidence.

広告掲載