I've open-sourced MCP Log Reader - an MCP server that helps you analyze and debug MCP server logs. It provides structured access to Claude's logs, making it easy to troubleshoot MCP integrations and understand AI-tool interactions.

What MCP Log Reader does: - Multi-platform support for macOS, Windows, and Linux with system-specific log paths - Smart filtering with case-insensitive text search for quick issue identification - Paginated browsing to navigate large log collections efficiently - Size management that handles large log files with intelligent truncation - Seamless Claude Desktop integration as a standard MCP server

The tool works by locating, sorting, and filtering MCP logs with a structured output format: - logs: Record of {filename: content} for each retrieved log file - pagination: Object with {currentPage, filesPerPage, totalFiles, totalPages, hasNextPage, hasPreviousPage} - logDirectory: String with the directory path where logs were found - message: Summary of operation results

Currently supports Claude Desktop with TypeScript implementation. Installation requires only cloning the repo and running with Node.js.

I'm building more tools to help debug MCP server and analyze AI-tool interactions. What challenges are you facing with MCP development or integration? What information would help you better understand how your tools interact with your MCP servers?

Links: - Repo: https://github.com/klara-research/MCP-Analyzer