MCP Sefaria Server MCP Server

An MCP ([Model Context Protocol](https://docs.anthropic.com/en/docs/agents-and-tools/mcp)) server that provides access to Jewish texts from the

Local serverstdioPython

What is the MCP Sefaria Server MCP server?

Mcp sefaria server mcp server connects MCP Sefaria Server to AI assistants that speak the Model Context Protocol. 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.

What MCP Sefaria Server does

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.

Key capabilities

  • 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

Tools it exposes

Once connected, the assistant can call these 4 tools directly:

  • get_text — Example: reference: "Genesis 1:1" reference: "שמות פרק ב פסוק ג" reference: "משנה ברכות פרק א משנה א"
  • get_commentaries — 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
  • get_daily_learnings — Retrieves the daily or weekly learning schedule from Sefaria's calendar API

Installing the mcp sefaria server mcp server

The server is distributed via npm as @smithery/cli, so most clients can run it without a manual build step. Add it to your MCP client's configuration and restart the client to pick it up — the copy-paste configs for Claude Desktop, Claude Code and Cursor are on this page.

Configuration

The server reads one environment variable: PYTHONIOENCODING. Keep credentials in your client's env block or a secrets manager rather than committing them.

Requirements

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

Where it fits

Productivity servers pay off through capture: the tasks and notes that never get filed are the ones where opening the app is more friction than the thought is worth. MCP Sefaria Server sits in that group, and the shape of its toolset — get_text, get_commentaries, search_texts among others — tells you what it is really for. Worth comparing against the other productivity servers in this directory before you commit to one, since several overlap in scope but differ sharply in setup cost and permissions.

Practical notes

  • This server runs locally, so it operates with whatever access your machine and its credentials already have. Scope that deliberately rather than by default.
  • Maintained by Sivan22, written in Python.
  • MCP clients ask for confirmation before each tool call by default. Keep that on while you learn what the mcp sefaria server mcp server actually does with your data.
  • Every entry in this directory is reviewed by hand before it goes live, and details are checked against the project's own documentation.

Available tools

ToolWhat it does
get_textExample: reference: "Genesis 1:1" reference: "שמות פרק ב פסוק ג" reference: "משנה ברכות פרק א משנה א"
get_commentariesExample: reference: "Genesis 1:1" reference: "שמות פרק ב פסוק ג" reference: "משנה ברכות פרק א משנה א"
search_textsSearches for Jewish texts in the Sefaria library based on a query.
get_daily_learningsRetrieves the daily or weekly learning schedule from Sefaria's calendar API.

How to install the MCP Sefaria Server MCP server

{
  "mcpServers": {
    "sefaria-server": {
      "command": "npx",
      "args": ["-y", "@smithery/cli"],
      "env": {
        "PYTHONIOENCODING": "your-value"
      }
    }
  }
}

Add to claude_desktop_config.json, then restart Claude Desktop.

Configuration

  • Python >= 3.10 - MCP SDK >= 1.1.1 - Sefaria API
VariableDescriptionRequired
PYTHONIOENCODINGConfiguration value read at startup.Optional

Example prompts to try

  • Use MCP Sefaria Server to get text.
  • Use MCP Sefaria Server to get commentaries.
  • Use MCP Sefaria Server to search texts.

Frequently asked questions

It connects MCP Sefaria Server to MCP-compatible AI assistants such as Claude and Cursor, exposing 4 tools (get_text, get_commentaries, search_texts, and more) that the assistant can call on your behalf. Instead of copying data back and forth by hand, the assistant works with MCP Sefaria Server directly.