National Library of Israel Search MCP

National Library of Israel Search MCP

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.

Category
Visit Server

README

šŸŒ National Library of Israel Search MCP

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.

šŸ¤” Why Use This?

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.

šŸ“š What You Can Discover

The National Library of Israel houses an extraordinary collection including:

  • Historical Documents: Ancient manuscripts, government records, and personal archives
  • Literary Works: Books, poetry, and writings in multiple languages
  • Visual Materials: Photographs, maps, illustrations, and artwork
  • Audio Collections: Music recordings, speeches, and oral histories
  • Cultural Artifacts: Items representing Jewish heritage and Israeli culture
  • Academic Resources: Research materials and scholarly publications

⚔ Getting Started

1. Install Claude Desktop

First, you need to install Claude Desktop if you haven't already:

  • Windows & Mac: Download from https://claude.ai/download
  • Linux: Use the AppImage or follow the installation instructions on the official website

Make sure you have Claude Desktop version ≄ 2.0 for MCP support.

2. Download or Clone

Option A: Download the packaged release

Download it from here.

  • Available for Windows (with .zip) and Linux (with .tar.gz).
  • Unzip the downloaded file.
  • Double-click to install:
    • install_mcp_server.bat (for Windows)
    • install_mcp_server.bash (for Linux)

āž” This will install and register the server with Claude Desktop.

Option B: Clone manually

git clone https://github.com/mula2812/NLI_AI_Search.git
cd nli_mcp

3. Make sure Python ≄ 3.10 is installed

Windows:

winget install Python.Python.3

Ubuntu/Debian:

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

4. Install Requirements

pip install -r requirements.txt

5. Run the Installer

Windows

.\install_mcp_server.bat

Linux

chmod +x install_mcp_server.bash
./install_mcp_server.bash

6. Launch Claude Desktop

  • Restart Claude Desktop.
  • After clicking the "Search and Tools" button that is near the + button in the search bar, you should now see a tool named: nli_mcp

If visible, you're ready to go!

šŸ” What It Does

This server provides:

  • šŸ¤– Natural Language Query Processing:

    • Converts everyday language into structured API calls.
    • Handles advanced disambiguation, topic inference, and multiple query generation.
  • šŸ“ø Image Extraction:

    • Automatically detects relevant thumbnails.
    • Falls back to IIIF manifests if no thumbnails are available.
  • šŸŽ§ Streaming Support:

    • Supports playback of media via MP4, HLS, or audio endpoints.
  • 🌐 Multilingual Responses:

    • Answers can be returned in Hebrew or English based on the user's input.

āš™ Tools Available

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

šŸŽ‰ Now You Can Enjoy Using It šŸ‘Øā€šŸ’»

Once installed:

  • Open Claude Desktop.
  • Ask any question involving books, authors, subjects, images, or topics.
  • For example:

    Books by Bialik published after 1920.

You'll get:

  • Search results
  • Metadata
  • Links to items
  • Images or thumbnails
  • In some cases, streaming content or IIIF resources

šŸ› ļø Troubleshooting & FAQ

šŸ”§ Plugin not appearing?

  • Ensure Claude Desktop is ≄ v2.0 and you restarted after install.
  • Ensure that the installation package or project is located only in a path that contains English characters.

šŸ’¬ 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.

šŸ”‘ "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.

  1. Double-check the NLI_API_KEY environment variable, to ensure it installed correctly.
  2. Another option is to create your own free KEY: Obtaining a personal API key is not essential for the project's initial function, as mentioned. However, if you want to get full access to all the data and capabilities the National Library offers, it is highly recommended to register and get your own API key.
  • Visit the National Library of Israel's Open Library API documentation Open Library API (click).
  • Follow the instructions to register and get your API key. You may need to contact the National Library for access.

šŸ¤ Contributing

I warmly welcome contributions to improve this project. To contribute, please follow these steps:

  1. Fork this repository to create your own copy.

  2. Make your changes in a new branch.

  3. Submit a pull request with a clear description of your changes.

I look forward to seeing your inventions and updates!

šŸ“¬ Contact & Support

Issues & Bugs: GitHub Issues

Discussions & Q&A: GitHub Discussions

License

This project is licensed under the MIT License with Commons Clause.

  • Personal, educational, and non-commercial use is allowed.
  • Commercial use, including selling, licensing, or using the software in any revenue-generating product or service, requires prior written permission and a separate commercial license agreement from Ilan Mulakandov.
  • This restriction applies even if the software was originally used for personal, educational, or non-commercial purposes that later lead to commercial use.
  • Users must retain the copyright notice and license text in all copies or substantial portions of the software.

🚨 Disclaimer

This project is not officially affiliated with the National Library of Israel, but it uses their free public OpenLibrary APIs.

Recommended Servers

playwright-mcp

playwright-mcp

A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.

Official
Featured
TypeScript
Magic Component Platform (MCP)

Magic Component Platform (MCP)

An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.

Official
Featured
Local
TypeScript
Audiense Insights MCP Server

Audiense Insights MCP Server

Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.

Official
Featured
Local
TypeScript
VeyraX MCP

VeyraX MCP

Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.

Official
Featured
Local
graphlit-mcp-server

graphlit-mcp-server

The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.

Official
Featured
TypeScript
Kagi MCP Server

Kagi MCP Server

An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.

Official
Featured
Python
E2B

E2B

Using MCP to run code via e2b.

Official
Featured
Neon Database

Neon Database

MCP server for interacting with Neon Management API and databases

Official
Featured
Exa Search

Exa Search

A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.

Official
Featured
Qdrant Server

Qdrant Server

This repository is an example of how to create a MCP server for Qdrant, a vector search engine.

Official
Featured