Fire in da houseTop Tip:Paying $100+ per month for Perplexity, MidJourney, Runway, ChatGPT and other tools is crazy - get all your AI tools in one site starting at $15 per month with Galaxy AI Fire in da houseCheck it out free

mcp-otzaria-server

MCP.Pizza Chef: Sivan22

The mcp-otzaria-server is an MCP server that provides Large Language Models with powerful, structured access to Jewish texts and literature. It supports full-text search with advanced query syntax including field-specific searches, Boolean operators, phrase search, and wildcards. The server returns relevance-scored results enriched with references, topics, and highlighted excerpts, making it ideal for integrating Jewish textual knowledge into AI workflows. It requires Python 3.10+ and offers a standardized MCP interface for seamless LLM integration.

Use This MCP server To

Enable LLMs to search Jewish texts via MCP protocol Perform advanced Boolean and field-specific text queries Retrieve relevance-ranked Jewish literature excerpts Integrate Jewish textual knowledge into AI applications Support phrase and wildcard searches in Jewish texts

README

Jewish Library MCP Server

An MCP (Model Context Protocol) server that provides powerful search capabilities for Jewish texts and literature. This server enables Large Language Models to search and reference Jewish texts through a standardized interface.

Features

  • Full-text search across Jewish texts and literature
  • Advanced query syntax support:
    • Field-specific search (text:term, reference:term, topics:term)
    • Boolean operators (AND, OR)
    • Required/excluded terms (+term, -term)
    • Phrase search ('exact phrase')
    • Wildcards (?, *)
  • Relevance-based 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 .

Running the Server

The server can be run directly:

uv --directory path/to/directory run jewish_library

Or through an MCP client that supports the Model Context Protocol. for claude desktop app and cline you should use the following config:

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

Available tools

The server provides a single tool through the MCP interface:

full_text_search

Performs a full-text search across the Jewish library 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 with topic filter
"four species" AND topics:sukkot

# Wildcard search
pray* AND reference:psalms

Search results include:

  • Reference information
  • Relevant topics
  • Highlighted excerpts showing query matches
  • Relevance score

Development

This project uses:

  • MCP SDK for server implementation
  • Tantivy for full-text search capabilities

Requirements

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

License

MIT License

mcp-otzaria-server FAQ

How do I install the mcp-otzaria-server?
Clone the GitHub repo, download the index file, and install dependencies with Python 3.10 or higher.
What search features does the server support?
It supports full-text search, field-specific queries, Boolean operators, phrase search, wildcards, and relevance scoring.
Can I get detailed search results?
Yes, results include references, topics, and highlighted excerpts for better context.
Is the server compatible with multiple LLM providers?
Yes, it works with any MCP-compatible LLM including OpenAI, Claude, and Gemini.
What is the required Python version?
Python 3.10 or higher is required to run the server.
How do I update the Jewish text index?
Download the latest index from the provided Google Drive link and replace the existing index files.
Does the server support complex query syntax?
Yes, it supports Boolean logic, required/excluded terms, phrase searches, and wildcards for flexible querying.
Can I customize the search fields?
The server supports field-specific searches like text, reference, and topics out of the box.