zim-mcp-server

ThinkInAI-Hackathon/zim-mcp-server

3.4

If you are the rightful owner of zim-mcp-server and would like to certify it and/or have it hosted online, please leave a comment on the right or send an email to henry@mcphub.com.

ZIM MCP Server enables large language models to access and search content within ZIM files for offline information retrieval.

ZIM MCP Server is a specialized server designed to facilitate the interaction between large language models and ZIM files, which are used for offline storage of large reference content like Wikipedia. Developed by Kiwix, the ZIM format allows for high compression and fast searching, making it ideal for environments without internet connectivity. The server provides a bridge for AI models to access these offline resources, enabling question answering and information retrieval without the need for network access. This is particularly beneficial in regions with limited internet connectivity, as it allows for the dissemination of knowledge and educational resources. By integrating with local AI models, ZIM MCP Server ensures that users can leverage the vast amount of information stored in ZIM files efficiently and effectively.

Features

  • Direct access to ZIM file content for AI models.
  • Supports offline information retrieval and question answering.
  • Facilitates high compression and fast searching of large datasets.
  • Promotes knowledge dissemination in regions with limited internet access.
  • Integrates with local AI models for efficient data utilization.

Usages

usage with Claude Desktop

"zim-mcp-server": {
  "command": "uv",
  "args": [
    "--directory",
    "path\\to\\zim-mcp-server",   // e.g., D:\\zim-mcp-server
    "run",
    "server.py",
    "path\\to\\zim\\files"      // e.g., D:\\ZIM
  ]
}

Tools

  1. list_zim_files

    List all ZIM files in allowed directories.

  2. search_zim_file

    Search within ZIM file content.

  3. get_zim_entry

    Get detailed content of a specific entry in a ZIM file.