MCP-Analyzer MCP Server

Use This MCP server To

Read MCP logs from standard locations on all platforms Filter MCP logs with case-insensitive text search Paginate through large MCP log collections efficiently Debug MCP integrations by analyzing detailed logs Monitor model-tool interactions via log inspection Manage large log files with size-aware loading

README

MCP Server: Analyze & Debug MCP Logs

🔍 Read logs from standard locations across all platforms

🔎 Filter, paginate, and analyze large log collections

🎯 Overview

MCP Log Reader is a specialized MCP server that helps you analyze and debug Model Context Protocol logs. It provides Claude with direct access to log files, making it easy to troubleshoot MCP integrations and understand how Claude interacts with your tools.

Multi-platform Support: Works on macOS, Windows, and Linux with platform-specific log paths
Smart Filtering: Find specific log entries with case-insensitive text search
Paginated Browsing: Navigate large log collections efficiently
Size Management: Handles large log files with intelligent truncation
Seamless Claude Integration: Works directly with Claude Desktop

🚀 Quick Start

Installing via Smithery

To install MCP Log Reader for Claude Desktop automatically via Smithery:

npx -y @smithery/cli install @klara-research/MCP-Analyzer --client claude

Installing Manually

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

🔌 Connecting 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.

📋 Available Parameters

The log reader supports these parameters:

Parameter	Description	Default
`lines`	Number of lines to read from each log file	100
`filter`	Text to filter log entries by (case-insensitive)	""
`customPath`	Custom path to log directory	OS-specific
`fileLimit`	Maximum number of files to read per page	5
`page`	Page number for pagination	1

💡 Example Usage

Ask Claude to use the log reader tool:

Can you check my MCP logs for any connection errors in the last day?

Or with specific parameters:

Can you look through MCP logs with filter="error" and lines=50 to find initialization issues?

⚙️ How It Works

The server automatically detects your OS and finds the appropriate log directory
It locates all MCP log files and sorts them by modification time (newest first)
The requested page of log files is retrieved based on pagination settings
Files are processed with size limits to prevent overwhelming responses
Filtered content is returned in a structured format with pagination details

📄 License

MIT License

MCP-Analyzer FAQ

How does MCP-Analyzer handle logs from different operating systems?

It supports macOS, Windows, and Linux by reading logs from platform-specific standard locations.

Can MCP-Analyzer filter specific entries in large log files?

Yes, it provides smart, case-insensitive text search filtering for precise log analysis.

How does MCP-Analyzer manage very large log files?

It uses pagination and size management techniques to efficiently browse and analyze large log collections.

Is MCP-Analyzer integrated directly with LLMs like Claude?

Yes, it provides Claude direct access to logs for seamless debugging within MCP clients.

Can MCP-Analyzer help understand model interactions with tools?

Yes, by analyzing logs it reveals how models like Claude interact with various MCP tools and APIs.

Does MCP-Analyzer support real-time log analysis?

While primarily for reading and analyzing existing logs, it supports efficient browsing that can aid near real-time debugging.

What platforms is MCP-Analyzer compatible with?

It is compatible with macOS, Windows, and Linux platforms, covering major desktop environments.