Lumen MCP
Hybrid TypeScript/Java MCP server for analyzing JVM Flight Recorder files, enabling AI agents to diagnose exceptions, slow SQL, network latency, and performance bottlenecks.
README
🧠 SnipeFactory: Lumen MCP Engine
JVM Flight Recorder (JFR) Forensic Engine for LLM
Hybrid TypeScript/Java MCP Server for Advanced JVM Analysis
Lumen MCP is the analytical brain of the Lumen ecosystem. It leverages a high-performance Java engine to parse JFR files and a TypeScript bridge to provide a seamless Model Context Protocol (MCP) interface for AI agents like Gemini and Claude.
✨ Key Features
- Hybrid Intelligence: Combines Java's deep JFR parsing power with Node.js's ecosystem compatibility.
- Exception Forensics: Trace hidden exceptions (Swallowed Exceptions) with full call chains.
- SQL & I/O Analytics: Pinpoint slow queries and socket latencies with line-level precision.
- Smithery Ready: Fully compatible with Smithery CLI for instant distribution.
🚀 Installation & Setup
1. Build the Project
Lumen MCP requires both Node.js (18+) and Java (11+) to build.
npm install
npm run build
(This command runs tsc for the bridge and ./gradlew installDist for the engine.)
2. Register with Gemini CLI
You can now run Lumen using the Node.js bridge (Recommended):
{
"mcpServers": {
"lumen": {
"command": "node",
"args": [
"/path/to/lumen-mcp/dist/server.js"
]
}
}
}
🔍 Diagnostic Tools
| Tool | Description |
|---|---|
analyze_exceptions |
Analyzes exception throw points and call chains. |
analyze_jdbc_queries |
Identifies slow SQL queries and their source lines (Java 11+). |
analyze_network_io |
Detects socket latency (Essential for Java 8 triage). |
analyze_hot_methods |
Pinpoints code lines consuming the most CPU cycles. |
analyze_memory_usage |
Analyzes GC health and object allocation hotspots. |
analyze_lock_contention |
Identifies thread synchronization bottlenecks. |
📖 Usage Example
"Gemini, use lumen to analyze
data/incident.jfr. Tell me why the database response is slow."
© 2026 SnipeFactory. All rights reserved.
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。
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。
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。
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。
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。
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。
e2b-mcp-server
使用 MCP 通过 e2b 运行代码。
Neon MCP Server
用于与 Neon 管理 API 和数据库交互的 MCP 服务器
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。