Skip to main content
Glama
Sefaria Jewish Library MCP Server

Sefaria Jewish Library MCP Server

by Sivan22

Sefaria Jewish Library MCP Server

An MCP (Model Context Protocol) server that provides access to Jewish texts from the Sefaria library. This server enables Large Language Models to retrieve and reference Jewish texts through a standardized interface.

Features

  • Retrieve Jewish texts by reference

  • Retrieve commentaries on a given text

  • Search the Jewish library for a query

  • Get daily/weekly learning schedule from Sefaria's calendar

Related MCP server: Sefaria Jewish Library MCP Server

Installation

Requires Python 3.10 or higher.

Clone the repository

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

Running the Server

The server can be run directly:

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

Installing via Smithery

To install Sefaria Jewish Library for Claude Desktop automatically via Smithery:

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

Available tools

The server provides the following tools through the MCP interface:

get_text

Retrieves a specific Jewish text by its reference.

Example:

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

get_commentaries

Retrieves a list of commentaries for a given text.

Example:

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

search_texts

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

Example:

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

get_daily_learnings

Retrieves the daily or weekly learning schedule from Sefaria's calendar API.

Parameters (all optional):

  • diaspora (boolean): When true, returns weekly Torah reading for diaspora. When false, returns Torah reading for Israel. Default: true

  • custom (string): If available, the weekly Haftarah will be returned for the selected custom

  • year, month, day (integers): Specific date (all three must be used together, or API falls back to current date)

  • timezone (string): Timezone name in accordance with IANA Standards

Example:

# Get current day's learning schedule
{}

# Get learning schedule for a specific date in Israel
{
  "diaspora": false,
  "year": 2024,
  "month": 12,
  "day": 25,
  "timezone": "Asia/Jerusalem"
}

Returns a formatted schedule including:

  • Weekly Torah portion (Parashat Hashavua) with aliyot

  • Haftarah reading

  • Daf Yomi (daily Talmud page)

  • Daily Mishnah, Rambam, and other learning cycles

  • Various Jewish learning programs and their daily selections

Development

This project uses:

image

Requirements

  • Python >= 3.10

  • MCP SDK >= 1.1.1

  • Sefaria API

License

MIT License

Available Tools

4 tools
get_commentariesC

get a list of references of commentaries for a jewish text

Inputs: reference (required).

get_daily_learningsC

get the daily or weekly learning schedule from Sefaria's calendar

Inputs: custom, day, diaspora, month, +2 more.

get_textC

get a jewish text from the jewish library

Inputs: reference (required).

search_textsC

search for jewish texts in the Sefaria library

Inputs: query (required), filters, size, slop.

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

Loading tool schema changelog…

    TDQS

    B3.2/5.0

    Scored across 4 tools

    Disambiguation5/5

    Each tool has a clearly distinct purpose with no overlap: get_commentaries retrieves commentary references, get_daily_learnings fetches calendar schedules, get_text obtains specific texts, and search_texts performs library searches. The descriptions are precise, making it easy for an agent to select the correct tool without confusion.

    Naming Consistency5/5

    All tool names follow a consistent verb_noun pattern using snake_case (e.g., get_commentaries, search_texts). The naming is uniform across all four tools, with 'get_' and 'search_' as clear action prefixes, enhancing predictability and readability.

    Tool Count4/5

    With 4 tools, the count is reasonable for a library server, covering core operations like retrieving texts, commentaries, schedules, and searching. It is slightly lean but well-scoped; adding tools for updates or user interactions could enhance it, but it's not incomplete.

    Completeness4/5

    The tool set covers essential read-only operations for a Jewish library domain: accessing texts, commentaries, schedules, and searches. Minor gaps exist, such as no update, delete, or user-specific functions (e.g., saving favorites), but agents can work effectively with the provided tools for core queries.

    Maintenance

    ActivityInactive
    ResponsivenessNo recent community issues

    Related MCP Connectors

    Related MCP Servers

    • A
      license
      Not graded
      quality
      D
      maintenance
      An MCP 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.
      23
      MIT
    • A
      license
      Not graded
      quality
      B
      maintenance
      Enables LLMs to access and search Jewish texts from the Sefaria library through 15 MCP tools, including text retrieval, search, and manuscript access.
      28
      MIT
    • A
      license
      Not graded
      quality
      C
      maintenance
      Enables AI agents to access and query the Sefaria digital library of Jewish texts through natural language or direct tool calls.
      65 npm
      1
      MIT