OpenZIM MCP is a modern, secure MCP server that enables AI models to access and search ZIM format knowledge bases offline with intelligent, structured access patterns.
{
"openzim-mcp": {
"command": "uv",
"args": [
"--directory", "/path/to/openzim-mcp",
"run", "python", "-m", "openzim_mcp",
"/path/to/zim/files"
]
}
}
Unlike basic file readers, OpenZIM MCP provides intelligent, structured access that LLMs need to effectively navigate and understand vast knowledge repositories.
Browse by namespace (articles, metadata, media) instead of blind searching. Get structured access to content organization.
Get article structure, relationships, and metadata for deeper understanding. Extract links and content connections.
Advanced filtering, auto-complete suggestions, and relevance-ranked results with namespace and content type filters.
Cached operations and pagination prevent timeouts on massive archives. Intelligent caching with TTL management.
Extract internal/external links to understand content connections. Build knowledge graphs from ZIM content.
Comprehensive input validation, path traversal protection, and secure resource management with type safety.
Get up and running with OpenZIM MCP in just a few minutes.
# Clone the repository
git clone https://github.com/cameronrye/openzim-mcp.git
cd openzim-mcp
# Install dependencies
uv sync
# Create directory for ZIM files
mkdir ~/zim-files
# Download ZIM files from Kiwix Library
# https://browse.library.kiwix.org/
# Start the MCP server
uv run python -m openzim_mcp /path/to/zim/files
# Or using make
make run ZIM_DIR=/path/to/zim/files
See OpenZIM MCP in action with real-world examples and API calls.
{
"name": "search_zim_file",
"arguments": {
"zim_file_path": "wikipedia_en_100_2025-08.zim",
"query": "artificial intelligence",
"limit": 5
}
}
Found 42 matches for "artificial intelligence", showing 1-5:
## 1. Artificial Intelligence
Path: Artificial_intelligence
Snippet: Artificial intelligence (AI) is intelligence demonstrated by machines...
## 2. Machine Learning
Path: Machine_learning
Snippet: Machine learning is a subset of artificial intelligence...
Comprehensive guides, API references, and community resources to help you get the most out of OpenZIM MCP.
Complete documentation of all available MCP tools, parameters, and response formats.
View API Docs →Step-by-step tutorial to get OpenZIM MCP running in your environment quickly.
Start Tutorial →Advanced configuration options, environment variables, and performance tuning.
Configure →Deep dive into the system architecture, components, and design decisions.
Learn More →Guidelines for contributing code, reporting issues, and joining the community.
Contribute →