WinLog-mcp
Provides programmatic access to ingest and query Windows event logs (especially Sysmon logs), enabling security monitoring, incident response, and log analysis automation.
README
🪟 WinLog-mcp
A Model Context Protocol (MCP) tool for retrieving and analyzing Windows event logs (e.g. Sysmon). WinLog-mcp provides programmatic access to ingest and query Windows event logs, making it ideal for security monitoring, incident response, and log analysis automation.
✨ Features
- Ingest Windows Sysmon logs and store them as files in a user-defined directory
- Query logs by timestamp, returning recent event entries for analysis or troubleshooting
- Seamless interoperability with MCP tools and ecosystem
📄 Log files format
- Log files are named with the format
<timestamp>_<log_type>.login the chosen storage path
MCP Server (tool, prompts,...)
🛠️ Available Tools
ingest_syslog: Ingests recent Sysmon logs and writes them to a filequery_syslog: Queries ingested logs by timestamp and returns recent events
📋 Requirements
- Operating System: Windows
- Python: 3.7 or higher
- Dependencies:
- pywin32
- mcp.server.fastmcp (or your MCP server implementation)
💾 Installation
Clone the repository and install dependencies:
pip install -r requirements.txt
🚀 Usage
🖥️ Sysmon Installation
Reference: Sysmon Installation Guideline
cd sysmon
install.bat
▶️ Running Directly
Run the tool as an MCP server:
python main.py --storage-path \\PATH\\TO\\logs\\
🧑💻 Development Mode
You can inspect or debug using the MCP Inspector:
# Run in development mode
python \\PATH\\TO\\main.py --storage-path \\PATH\\TO\\logs\\
# Run in inspector mode
npx @modelcontextprotocol/inspector python \\PATH\\TO\\main.py --storage-path \\PATH\\TO\\logs\\
⚙️ Configuration
MCP configuration to run winlog-mcp tool.
{
"mcpServers": {
"winlog-mcp": {
"command": "python",
"args": [
"\\PATH\\TO\\main.py",
"--storage-path",
"\\PATH\\TO\\logs\\"
]
}
}
}
🤖 MCP Clients Integration
💬 Claude Desktop Integration
The configuration file is located at:
- Windows:
%APPDATA%\Claude\claude_desktop_config.json
Once integrated with Claude Desktop, you can ask Claude to:
Please show me the last 10 events in the last 24 hours, and Analyze them.

📄 License
This project is licensed under the MIT License - see the LICENSE file for details.
推荐服务器
Baidu Map
百度地图核心API现已全面兼容MCP协议,是国内首家兼容MCP协议的地图服务商。
Playwright MCP Server
一个模型上下文协议服务器,它使大型语言模型能够通过结构化的可访问性快照与网页进行交互,而无需视觉模型或屏幕截图。
Audiense Insights MCP Server
通过模型上下文协议启用与 Audiense Insights 账户的交互,从而促进营销洞察和受众数据的提取和分析,包括人口统计信息、行为和影响者互动。
Magic Component Platform (MCP)
一个由人工智能驱动的工具,可以从自然语言描述生成现代化的用户界面组件,并与流行的集成开发环境(IDE)集成,从而简化用户界面开发流程。
VeyraX
一个单一的 MCP 工具,连接你所有喜爱的工具:Gmail、日历以及其他 40 多个工具。
Kagi MCP Server
一个 MCP 服务器,集成了 Kagi 搜索功能和 Claude AI,使 Claude 能够在回答需要最新信息的问题时执行实时网络搜索。
graphlit-mcp-server
模型上下文协议 (MCP) 服务器实现了 MCP 客户端与 Graphlit 服务之间的集成。 除了网络爬取之外,还可以将任何内容(从 Slack 到 Gmail 再到播客订阅源)导入到 Graphlit 项目中,然后从 MCP 客户端检索相关内容。
Exa MCP Server
模型上下文协议(MCP)服务器允许像 Claude 这样的 AI 助手使用 Exa AI 搜索 API 进行网络搜索。这种设置允许 AI 模型以安全和受控的方式获取实时的网络信息。
mcp-server-qdrant
这个仓库展示了如何为向量搜索引擎 Qdrant 创建一个 MCP (Managed Control Plane) 服务器的示例。
e2b-mcp-server
使用 MCP 通过 e2b 运行代码。