MCP Sefaria Server

🚀 Sefaria Jewish Library MCP Server

A server adhering to the Model Context Protocol (MCP), providing access to Jewish texts in the Sefaria library. This server enables large language models to retrieve and reference Jewish texts through a standardized interface.

🚀 Quick Start

This server allows large language models to access and reference Jewish texts in the Sefaria library via a standardized interface.

✨ Features

• Retrieve specific Jewish texts by reference.
• Obtain commentaries for a given text.
• Search for queries in the Jewish library.

📦 Installation

Python 3.10 or higher is required.

Clone the repository

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

Run the server

You can run the server directly:

uv --directory path/to/directory run sefaria_jewish_library

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

{
  "mcpServers": {        
      "sefaria_jewish_library": {
          "command": "uv",
          "args": [
              "--directory",
              "absolute/path/to/mcp-sefaria-server",
              "run",
              "sefaria_jewish_library"
          ],
          "env": {
            "PYTHONIOENCODING": "utf-8" 
          }
      }
  }
}

Install using Smithery

Automatically install the Sefaria Jewish Library for the Claude desktop via Smithery:

npx -y @smithery/cli install mcp-sefaria-server --client claude

💻 Usage Examples

Available Tools

The server provides the following tools through the MCP interface:

get_text

Retrieve a specific Jewish text by reference.

Example:

reference: "Genesis 1:1"
reference: "שמות פרק ב פסוק ג"
reference: "משנה ברכות פרק א משנה א"

get_commentaries

Obtain a list of commentaries for a given text.

Example:

reference: "Genesis 1:1"
reference: "שמות פרק ב פ斯וק ג"
reference: "משנה ברכות פרק א משנה א"

search_texts

Search for Jewish texts in the Sefaria library based on a query.

Example:

query: "moshiach"
slop: 1
filters: ["Talmud", "Bavli"]
size: 5

🔧 Technical Details

This project uses:

• MCP SDK to implement the server.
• Sefaria API to access Jewish texts.

Requirements

• Python >= 3.10
• MCP SDK >= 1.1.1
• Sefaria API

📄 License

MIT License