Torah MCP
MCP serverAI & modelsYour AI can study the Torah from the real texts, quoting verses exactly as they appear and never making passages up. This adds source discipline to Torah study, so answers stay grounded in what the texts actually say.
Use Torah MCP in Claude, ChatGPT or Ahel Desktop
Free. Sign in, add Torah MCP and connect your AI. About a minute.
Also: Claude Code · Cursor · Codex
Then ask your AI: use the sefaria text tool from Torah MCP
No key or account is asked for. Not verified by us yet: Ahel has not run a call through it.
Details
Available today. Use it from your connected AI after setup.
No key or account is asked for. Not verified by us yet: Ahel has not run a call through it.
Add it to your AI, then ask it to study or quote from the Torah and it will read from the real texts instead of relying on memory.
What your AI can do with it
- Read the real Torah texts
- Quote verses exactly as written
- Ground study answers in actual sources
- Avoid invented or misremembered passages
Install Torah MCP
The server’s own address, for the clients that take one directly. Or connect Ahel once and every client you use reads it from one address, with the account kept on Ahel rather than in each client’s config.
Claude Code
claude mcp add --transport http --scope user torah-mcp 'https://torah-mcp.com/mcp'Run it once in your project, then open /mcp to approve any sign-in the server asks for.
Claude Desktop
https://torah-mcp.com/mcpAdd a custom connector in Settings, paste this address, and approve the sign-in.
Cursor
cursor://anysphere.cursor-deeplink/mcp/install?name=torah-mcp&config=eyJ1cmwiOiJodHRwczovL3RvcmFoLW1jcC5jb20vbWNwIn0=Open the link and Cursor adds the server at that address.
ChatGPT
https://torah-mcp.com/mcpIn Settings, enable Developer mode, create an MCP app, and paste this address. Your plan and workspace must allow custom apps.
Codex
codex mcp add torah-mcp --url 'https://torah-mcp.com/mcp'Run it once, then sign in with codex mcp login torah-mcp if the server asks for an account.
From the project's README
As published by jonathanb555/torah-mcp in README.md.
A source discipline for Claude — never quote Torah from model memory. Before answering any religious question, Claude loads a bundled study method that forces it to read the actual texts (Sefaria API), quote exactly, flag divergent opinions, and point to hebrewbooks.org for further study — never fabricating a reference. A HebrewBooks catalog search (~65,000 seforim) completes the loop.
Pairs ideally with Sefaria's official MCP
(https://mcp.sefaria.org/sse) — install both: the official server for deep
library access (14 tools), Torah MCP for the citation discipline, the study
method and HebrewBooks.
Free, no account, no data collected. Hosted instance:
https://torah-mcp.com/mcp
Install
claude.ai — Settings → Connectors → Add custom connector → paste the URL above. Works on mobile too once added.
Claude Code
claude mcp add --transport http torah https://torah-mcp.com/mcp
Any MCP client — streamable HTTP transport at the same URL.
Tools
| Tool | Purpose |
|---|---|
hebrewbooks_skill | The core: the study method loaded before answering any religious question — sources actually read, exact quotes, hebrewbooks.org reading links |
hebrewbooks_search | HebrewBooks catalog search (~65,000 scanned seforim) by title/author via their official API — requires a HEBREWBOOKS_API_KEY (granted on request: developers@hebrewbooks.org) |
mode_etude | Study register — debutant (all in French, every term explained, for readers with no background or no Hebrew), classique (bilingual, default), avance (beit midrash: original text, no glosses, mahloket, girsaot, lomdus). Same source discipline in all three |
havrouta_mode | Study-partner mode: Claude asks the questions, makes you defend Rashi against Tosafot, never hands out answers |
guide_paracha | AlHaTorah-style weekly study guide: aliyot, three textual questions with diverging commentators, haftarah echo, Shabbat-table questions |
daf_viewer | MCP App: an interactive Vilna page in the conversation (Gemara, Rashi, Tosafot, click-to-translate). Also at /daf |
zmanim · date_hebraique · gematria · nikoud · fiche_source | Daily-life tools: Hebcal times, Hebrew dates, 5-method gematria, Dicta vocalization, WhatsApp-ready source cards |
sefaria_text | Text of any reference (Hebrew + translation — French first when Sefaria has it, e.g. Bible du Rabbinat for Tanakh, else English): Berakhot 2a, Shulchan Arukh, Orach Chayim 1:1… |
sefaria_links | Linked commentaries and sources (Rashi, Tosafot, midrash, halakhah…), filterable by category |
sefaria_search | Full-text search across the whole library (Hebrew or English) |
sefaria_calendar | Parashat hashavua, haftarah, daf yomi, daily Rambam… |
The server also ships an instructions block (loaded by MCP clients at
initialize) telling the model to load the skill before answering any religious
question, and five MCP prompts (hebrewbooks, havrouta, paracha, debutant, avance).
The website — Mamash IA
The website now lives under its own brand, Mamash IA (the connector keeps
its torah-mcp identity; torah-mcp.com redirects, and torah-mcp.com/mcp keeps
serving installed connectors forever). Everything the MCP does also exists on the web, no install needed, in three
languages: French at the root (mamash-ia.com),
English under /en, Hebrew (RTL) under
/he — same slugs everywhere (/question, /daf,
/outils, /install, /daily, /privacy), a FR · EN · עב switcher on
every page, hreflang links for search engines.
/question— ask in plain language; Claude runs server-side with the same tools and method and answers in the language of the page, with the sources it actually read (copy / share / local history)./daf— the Vilna-style daf viewer;/outils— zmanim, Hebrew date, gematria, nikkud, source sheets;/daily— today's study cycles.
Optional secrets for the site: ANTHROPIC_API_KEY (enables /question),
STATS_PASSWORD (private /stats page over the D1 question log — no IPs).
Deploy your own
Or manually:
npm install
npx wrangler deploy
No secrets required. Optional: set a BEARER_TOKENS secret (comma-separated
list) to switch from public access to invitation-only — each guest then uses
https://<your-worker>/<token>/mcp, and you revoke by removing a token.
Good-citizen notes
- Requests to Sefaria carry an identifying
User-Agentand are edge-cached (24 h for texts and links, 1 h for calendars) so repeated study of the same daf costs Sefaria a single API call. - A per-IP rate limit (60 req/min) protects the public endpoint.
- Text licenses are returned with every response. Data by the wonderful Sefaria — support them.
License
MIT — see LICENSE. The bundled study-method skill and this server are unaffiliated with Sefaria and hebrewbooks.org.
Tools it offers (16)
What this server listed when Ahel dialed its public endpoint in Sep 2026, with no key and no account of yours. The names are the server’s own.
sefaria_textsefaria_linkssefaria_searchsefaria_calendarhebrewbooks_skillhavrouta_modemode_etudehebrewbooks_searchguide_parachazmanimdate_hebraiquegematrianikoudmot_chabbatfiche_sourcedaf_viewer
Signals
- GitHub stars
- 1
- Last commit
- Sep 2026
Advanced
- Delivery
- torah-mcp MCP server → your Ahel connector (mcp.ahel.ai) → your AI.
- Item type
- mcp-server
- Key
io-github-jonathanb555-torah-mcp- Source
- github.com/jonathanb555/torah-mcp
- Hosted endpoint
https://torah-mcp.com/mcp
github.com/jonathanb555/torah-mcp
More in AI & models
MCP server · upstash
More in AI & modelsAdButler
MCP server · adbutler
More in AI & modelsatom-mcp-server
MCP server · a7om-ai
More in AI & modelsottasia
MCP server · aiweather-anurag
More in AI & modelsunphurl
MCP server · 123ergo
More in AI & modelsmicrosoft-learn-mcp
MCP server · microsoftdocs
More in AI & models