loading…
Search for a command to run...
loading…
Enables natural language search of the National Library of Israel's digital archive using Claude. Converts conversational queries into structured API calls for
Enables natural language search of the National Library of Israel's digital archive using Claude. Converts conversational queries into structured API calls for exploring cultural, historical, and literary assets.
Welcome to the National Library of Israel Model Context Protocol (NLI MCP) - a modern AI-powered bridge for exploring millions of cultural, historical, and literary assets held by the National Library of Israel (NLI).
This MCP server allows natural language search using Claude, making it easier than ever to search the NLI digital archive through conversational queries in Hebrew or English.
The NLI API is powerful but complex. It requires structured metadata-based queries that are hard to construct without technical or library-specific knowledge. This MCP bridges that gap by converting simple questions like:
"medieval Hebrew manuscripts"
into rich API calls that return accurate and media-rich results with thumbnails, manifests, or streaming content when available.
The National Library of Israel houses an extraordinary collection including:
First, you need to install Claude Desktop if you haven't already:
Make sure you have Claude Desktop version ≥ 2.0 for MCP support.
Download it from here.
install_mcp_server.bat (for Windows)install_mcp_server.bash (for Linux)➡ This will install and register the server with Claude Desktop.
git clone https://github.com/mula2812/NLI_AI_Search.git
cd nli_mcp
winget install Python.Python.3
sudo apt update
sudo apt install python3.10 python3.10-venv python3.10-distutils -y
To optionally set Python 3.10 as the default:
sudo update-alternatives --install /usr/bin/python3 python3 /usr/bin/python3.10 1
sudo update-alternatives --config python3
pip install -r requirements.txt
.\install_mcp_server.bat
chmod +x install_mcp_server.bash
./install_mcp_server.bash
nli_mcpIf visible, you're ready to go!
This server provides:
🤖 Natural Language Query Processing:
📸 Image Extraction:
🎧 Streaming Support:
🌐 Multilingual Responses:
| Tool Name | Purpose |
|---|---|
process_natural_query |
Converts a natural language query into structured API parameters |
generate_response |
Fetches results, extracts images, and builds a user-facing response |
stream_batches |
Streams large result sets for long or segmented queries |
get_image |
Retrieves IIIF image by identifier |
get_manifest |
Retrieves IIIF manifest JSON for a given record |
get_stream |
Retrieves MP4/HLS/audio streams associated with a library record |
Once installed:
Books by Bialik published after 1920.
You'll get:
🔧 Plugin not appearing?
💬 MCP isn't responding. What should I do?
Make sure you installed it correctly. You should see in search and tools the "nli_mcp" addition.
Ensure you enable all the "nli_mcp" inside options (from the search and tools options).
Check your internet connection and firewall settings.
Review the logs for any error messages.
🔑 "Invalid API key" error
As a default visitor key is installed to your computer using the bat or bash file, which allows basic access to the library data.
I warmly welcome contributions to improve this project. To contribute, please follow these steps:
Fork this repository to create your own copy.
Make your changes in a new branch.
Submit a pull request with a clear description of your changes.
I look forward to seeing your inventions and updates!
Issues & Bugs: GitHub Issues
Discussions & Q&A: GitHub Discussions
This project is licensed under the MIT License with Commons Clause.
This project is not officially affiliated with the National Library of Israel, but it uses their free public OpenLibrary APIs.
Выполни в терминале:
claude mcp add national-library-of-israel-search-mcp -- npx Безопасность
Низкий рискАвтоматическая эвристика по публичным данным — не гарантия безопасности.