About Jewish Library MCP Server
An MCP server that makes a Jewish text library searchable by LLMs through a standard interface. It uses Tantivy for full-text search and targets users who need to reference Jewish texts.
Key features
- 01Full-text search across Jewish texts
- 02Field-specific, boolean and phrase queries
- 03Required and excluded term syntax
- 04Relevance-based result scoring
- 05Results with references, topics and excerpts
Use cases
- 01Finding passages on a topic in Jewish literature
- 02Providing source references for LLM answers
- 03Filtering library content by topic or reference
MCP support
The project runs as an MCP server that exposes a full_text_search tool to MCP clients for querying the Jewish library index.
Configuration
Local server config is the same for every client. Copy it into your client’s MCP config file.
We haven’t collected a package or remote endpoint for this server. Follow the instructions in the project README.
Tools
Local servers expose tools only once running on your machine, and the maintainer has not provided a tool list.
Details
From the project READMEJewish 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:
Requirements
- Python >= 3.10
- MCP SDK >= 1.1.1
- Tantivy search engine
License
MIT License
Comments
New to MCP?
From what the protocol is to installing your first server, these answers cover most first questions.
An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.