MCP Analyzer

🚀 MCP Server: Analyze and Debug MCP Logs

This MCP server helps you analyze and debug Model Context Protocol (MCP) logs, enabling easy troubleshooting of MCP integration issues and understanding of how Claude interacts with your tools.

🚀 Quick Start

Install directly from GitHub:

# Clone the repository
git clone https://github.com/klara-research/MCP-Analyzer.git
cd MCP-Analyzer

# Install dependencies
npm i

Build and run:

# Compile TypeScript
npx tsc

✨ Features

• Multi-platform support: Works on macOS, Windows, and Linux, with platform-specific log paths.
• Intelligent filtering: Find specific log entries through case-insensitive text search.
• Paged browsing: Efficiently navigate large log collections.
• Capacity management: Has intelligent truncation when dealing with large files.
• Seamless integration with Claude: Works directly with Claude Desktop.

🔌 Connect to Claude

Add the server to your Claude Desktop configuration:

{
  "mcpServers": {
    "log-reader": {
      "command": "node",
      "args": [
        "/absolute/path/MCP-Analyzer/build"
      ]
    }
  }
}

Then restart Claude Desktop.

📦 Installation

📋 Available Parameters

The log reader supports the following parameters:

💻 Usage Examples

Basic Usage

Let Claude use the log reading tool:

Can you check if there are any connection errors in my MCP logs from the past day?

Advanced Usage

Or use specific parameters:

Can you filter for "error" and set lines=50 to find initialization issues?

🔧 Technical Details

1. The server automatically detects your operating system and finds the appropriate log directory.
2. It locates all MCP log files and sorts them by modification time (newest first).
3. Retrieves the requested page according to the pagination settings.
4. Files are processed with size limits to prevent response overload.
5. The filtered content is returned in a structured format, along with pagination details.

📄 License

MIT License