OpenZIM

Provides offline access to ZIM format knowledge bases with search capabilities, content retrieval, and smart fallback mechanisms for accessing Wikipedia dumps and educational archives without internet connectivity.

This OpenZIM MCP server by Cameron Rye enables AI models to access and search ZIM format knowledge bases offline, providing tools for listing ZIM files, searching content with configurable limits and offsets, and retrieving specific entries with smart fallback mechanisms. Built with Python and featuring a modular architecture with comprehensive security validation, intelligent caching with LRU eviction and TTL support, and HTML content processing with BeautifulSoup, it offers robust path validation to prevent directory traversal attacks, instance tracking to prevent configuration conflicts, and automatic path mapping for reliable entry retrieval. The implementation includes extensive testing coverage, performance benchmarks, and development tooling with pre-commit hooks, making it ideal for researchers and developers who need AI-assisted access to offline Wikipedia dumps, educational content archives, and other ZIM-formatted knowledge repositories without requiring internet connectivity.