MCP Otzaria Server

🚀 Jewish Library MCP Server

A powerful MCP (Model Context Protocol) server for searching Jewish texts and literature. This server enables large language models to search and reference Jewish texts through a standardized interface.

🚀 Quick Start

The Jewish Library MCP Server is a specialized server designed to facilitate searching and referencing of Jewish texts and literature. It provides large language models with a standardized interface to access these resources.

✨ Features

• Full-text search of Jewish texts and literature.
• Support for advanced query syntax:
  • Field-specific search (text:term, reference:term, topics:term).
  • Boolean operators (AND, OR).
  • Required or excluded words (+term, -term).
  • Phrase search ('exact phrase').
  • Wildcards (?, *).
• Relevance scoring.
• Rich search results including references, topics, and highlighted excerpts.

📦 Installation

Requires Python 3.10 or higher.

Clone the repository

git clone https://github.com/sivan22/mcp-otzaria-server.git
cd mcp-otzaria-server

Get the index

Download and extract the index from here.

Install dependencies

pip install .

💻 Usage Examples

Basic Usage

You can run the server directly:

uv --directory your_path/to/directory run jewish_library

Advanced Usage

Or run it through an MCP client that supports the Model Context Protocol. For the Claude desktop application and command-line tools, use the following configuration:

{
  "mcpServers": {        
      "jewish_library": {
          "command": "uv",
          "args": [
              "--directory",
              "your_path/to/directory",
              "run",
              "jewish_library"
          ],
          "env": {
            "PYTHONIOENCODING": "utf-8" 
          }
      }
  }
}

Available Tools

The server provides a tool through the MCP interface:

full_text_search

Perform a full-text search with advanced query capabilities.

Example query formats:

# Basic search
"maimonides on prayer"

# Field-specific search
text:"love your neighbor" AND topics:mitzvot

# Required terms
+shabbat +candles

# Phrase search and topic filtering
"four species" AND topics:sukkot

# Wildcard search
pray* AND reference:psalms

Search results include:

• Reference information.
• Related topics.
• Highlighted excerpts showing query matches.
• Relevance scoring.

🔧 Technical Details

This project uses:

• MCP SDK for server implementation.
• Tantivy to provide full-text search functionality.

Requirements

• Python >= 3.10
• MCP SDK >= 1.1.1
• Tantivy search engine

📄 License

MIT License