LogScribe MCP

LogScribe MCP

Handles log file management and analysis with tools to list, read, search, filter, and generate analytics on log files.

Category
访问服务器

README

LogScribe MCP

A Model Context Protocol (MCP) server for log file management and analysis with enhanced formatting and error handling.

✨ Features

  • 📁 List Log Files - View all .log files with size and modification metadata
  • 📖 Read Log Files - Read the last N lines with line numbers and formatting
  • 🔍 Search Individual Files - Search for patterns within specific log files
  • 🌐 Cross-File Search - Search patterns across all log files simultaneously
  • 🏷️ Filter by Log Level - Filter entries by ERROR, WARN, INFO, DEBUG, CRITICAL
  • 📊 Generate Analytics - Comprehensive log file summaries and statistics
  • ✅ Error Handling - Graceful handling of missing files and edge cases
  • 🎨 Rich Output - Formatted output with emojis and visual separators
  • 🔧 Hot Reload - Auto-restart on file changes during development

Quick Start

  1. Install dependencies:

    pip install -r requirements.txt
    
  2. Create logs directory (optional):

    mkdir logs
    # Add some .log files to test
    echo "2024-01-01 INFO Application started" > logs/app.log
    

    (You could also use sample logs in the logs folder to get started.)

  3. Run the server:

    # Use default ./logs directory
    python mcp_server.py
    
    # Use custom logs directory (command line)
    python mcp_server.py /path/to/your/logs
    
    # Use custom logs directory (environment variable)
    LOGS_DIR="/path/to/your/logs" python mcp_server.py
    
    # Development (with hot reload)
    python dev_server.py
    

Available Tools

list_files()

Lists all .log files in the ./logs directory with file size information.

Example output:

📁 Log Files:
app.log (2.5 KB)
error.log (1.2 KB)

read_file(filename: str, lines: int = 10)

Reads the last N lines from a specified log file with enhanced formatting.

Parameters:

  • filename: Name of the log file (e.g., "app.log")
  • lines: Number of lines to read from the end (default: 10)

Example output:

📄 app.log (showing last 3 of 100 lines)
──────────────────────────────────────────────────
  98 | 2024-01-01 10:00:00 INFO Application started
  99 | 2024-01-01 10:01:00 DEBUG Loading configuration
 100 | 2024-01-01 10:02:00 INFO Ready to serve requests

search_logs(filename: str, pattern: str, lines: int = 20)

Searches for a pattern within a specific log file using case-insensitive regex.

Parameters:

  • filename: Name of the log file to search
  • pattern: Search pattern (supports regex)
  • lines: Maximum number of matching lines to return (default: 20)

search_all_logs(pattern: str, max_results: int = 50)

Searches for a pattern across ALL log files simultaneously.

Parameters:

  • pattern: Search pattern (supports regex)
  • max_results: Maximum number of matching lines to return (default: 50)

log_summary(filename: str)

Generates comprehensive analytics and statistics for a log file.

Parameters:

  • filename: Name of the log file to analyze

Claude Desktop Integration

Add to your claude_desktop_config.json:

Option 1: Default logs directory

{
  "mcpServers": {
    "log-server": {
      "command": "/full/path/to/your/venv/bin/python",
      "args": ["/full/path/to/your/mcp_server.py"],
      "cwd": "/full/path/to/your/project"
    }
  }
}

Option 2: Custom logs directory (command line)

{
  "mcpServers": {
    "log-server": {
      "command": "/full/path/to/your/venv/bin/python",
      "args": ["/full/path/to/your/mcp_server.py", "/path/to/your/logs"],
      "cwd": "/full/path/to/your/project"
    }
  }
}

Option 3: Custom logs directory (environment variable)

{
  "mcpServers": {
    "log-server": {
      "command": "/full/path/to/your/venv/bin/python",
      "args": ["/full/path/to/your/mcp_server.py"],
      "cwd": "/full/path/to/your/project",
      "env": {
        "LOGS_DIR": "/path/to/your/logs"
      }
    }
  }
}

Configuration

Logs Directory

The server supports three ways to specify where your log files are located:

  1. Default: Uses ./logs directory in the project folder
  2. Command Line: Pass directory path as first argument
    python mcp_server.py /var/log/myapp
    
  3. Environment Variable: Set LOGS_DIR environment variable
    export LOGS_DIR="/var/log/myapp"
    python mcp_server.py
    

Priority order: Command Line > Environment Variable > Default

Example Usage

Ask Claude:

  • "List all my log files"
  • "Show me the last 20 lines from app.log"
  • "Read the last 5 lines from error.log"
  • "Search for 'ERROR' in app.log"
  • "Show me all ERROR entries in app.log"
  • "Search for 'PaymentService' across all my logs"
  • "Generate a summary of app.log"

Error Handling

The server gracefully handles:

  • Missing log files (returns helpful error message)
  • Empty log files (indicates file is empty)
  • Invalid file paths

Requirements

  • Python 3.8+
  • mcp>=1.9.3
  • watchdog>=3.0.0 (for development hot reload)
  • pytest>=8.4.0 (for running tests)

Testing

Run the included tests to verify everything works:

# Simple test runner
python tests/test_basic.py

# Or using pytest (install first: pip install pytest)
pytest tests/ -v

Tests cover:

  • Server initialization and configuration
  • Log directory selection logic (env vars, command line args)
  • Basic functionality verification

Development

For development with automatic restart on file changes:

python dev_server.py

The development server will automatically restart when you modify any .py files, making it easier to test changes without manually restarting.

推荐服务器

Baidu Map

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。

官方
精选
JavaScript
Playwright MCP Server

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。

官方
精选
TypeScript
Magic Component Platform (MCP)

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。

官方
精选
本地
TypeScript
Audiense Insights MCP Server

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。

官方
精选
本地
TypeScript
VeyraX

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。

官方
精选
本地
graphlit-mcp-server

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。

官方
精选
TypeScript
Kagi MCP Server

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。

官方
精选
Python
e2b-mcp-server

e2b-mcp-server

使用 MCP 通过 e2b 运行代码。

官方
精选
Neon MCP Server

Neon MCP Server

用于与 Neon 管理 API 和数据库交互的 MCP 服务器

官方
精选
Exa MCP Server

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。

官方
精选