TokenScope

Scans codebases to intelligently extract and prioritize files for LLMs while respecting token limits and .gitignore patterns

TokenScope is a token-aware directory explorer for Large Language Models that enables intelligent codebase analysis while respecting token limitations. Built by Carlos Gaete-Morales, this Python-based MCP server provides tools for scanning directory structures, extracting file contents, analyzing token usage statistics, and generating comprehensive reports. It features security validation to restrict operations to specified base directories, intelligent file prioritization based on importance, and automatic handling of common file formats like JSON. The implementation respects .gitignore files and includes default ignore patterns for common non-source directories, making it valuable for developers who need to help LLMs understand codebases efficiently without exceeding token limits.