Specialised AI tools for ecclesiastical Latin

Read Latin church documents
with AI assistance

Extract dates, places, names, scripture allusions, and catalogue-ready metadata from Catholic Latin records — necrologies, chapter acts, episcopal letters, charters. Connects to Claude, Codex, Cursor, Windsurf, and any MCP-compatible AI assistant.

Church Latin AI connects to your existing AI assistant. It is not a standalone web editor — you need Claude, Codex, Cursor, or a similar tool to use it.

2,300+ Diocese place-names
147 Countries covered
37,228 Vulgate verses indexed
9 Specialised tools

See it in action

A single necrology entry, processed in seconds.

Latin input

Obiit fr. Joannes Brady, O.C.D., natus die III Kal. Septembris anno MDCCCXLV, professus anno MDCCCLXVIII, sacerdos factus anno MDCCCLXXII, Prior Conventus Dubliniensis per annos quinque. Obiit Dublini die XV Martii anni MDCCCCXX, anno aetatis LXXV, professionis LII.

Extracted metadata

NameJoannes Brady
OrderDiscalced Carmelites (O.C.D.)
Born1845-08-30 (confidence: high)
Professed1868
Ordained1872
OfficePrior, Dublin Convent (5 years)
Place of deathDublin, Ireland
Date of death1920-03-15 (confidence: high)
Age at death75 ✓ cross-checked
Years professed52 ✓ cross-checked

Ready to export as AtoM CSV, Dublin Core, EAD XML, or JSON.

Built for the archive room

Ecclesiastical Latin has its own conventions — Kalends and Ides for dates, diocese adjectivals for places, clerical abbreviations that no general-purpose AI reliably handles. These tools are built around that domain knowledge.

📅

Dates in any Catholic format

Kalends, Nones, Ides. Feast-day anchors ("in festo S. Michaelis"). Pontifical regnal years. Indictions. All converted to ISO 8601.

🗺️

Worldwide diocese gazetteer

2,300+ Latin diocese adjectivals mapped to modern cities and countries — Ireland, Italy, Germany, Africa, the Americas, Asia. Handles declined inflected forms.

📖

Vulgate scripture detection

37,228 Clementine Vulgate verses in full-text search. Detects verbatim quotations, partial citations, and allusions. Returns the Douay-Rheims translation.

🗂️

Export in archival standards

Extracted metadata exports to AtoM CSV (ISAD(G)), Dublin Core, EAD 2002 XML, or plain JSON — ready to import directly into your catalogue.

What it does


All plans
Expands clerical abbreviations, converts Latin dates, normalises spelling, identifies diocese and place names, detects Vulgate quotations, and triages batches of up to 50 documents at once.
Pro / Institutional
Everything above, plus full structured metadata extraction from necrologies, chapter acts, and letters — and export to AtoM CSV, Dublin Core, EAD XML, or JSON.

Try it free

50 tool calls per month. No credit card required.
Enter your email and your API key arrives in seconds.

Pricing

Pay by card through Stripe. Your API key is emailed to you automatically. Cancel any time.

Individual
€9 / month
200 tool calls per month
≈ occasional research, a handful of documents
  • All free-tier tools
  • Latin date conversion
  • Worldwide diocese gazetteer
  • Vulgate scripture search
  • Batch document triage
  • Extract structured metadata
  • Export to AtoM CSV, EAD, Dublin Core
Subscribe — Individual
Team / Archive Office
€79 / month
10,000 tool calls per month
≈ active archive office, shared team use
  • Everything in Professional
  • High-volume batch processing
  • Suitable for shared archive office use
  • Priority support by email
Subscribe — Team
Institutional
Annual contract
Diocese · Seminary · Religious Order · Archive
  • Custom volume and user seats
  • Onboarding and workflow review
  • Data governance and privacy review
  • Dedicated support
  • Pilot project option available
Contact us to discuss

Payments handled securely by Stripe. API key sent to your billing email within minutes of subscribing.

Connect your AI assistant

1

Get an API key

Try free (50 calls/month, no card needed) or subscribe above for higher limits. Your key arrives by email.

2

Add the server to your client

Use the MCP endpoint URL and your API key in your client's configuration.

3

Start processing documents

Paste a Latin text and ask your AI assistant to extract metadata, find toponyms, or detect a scripture allusion.

Claude Code (CLI)

Run once in your terminal:

claude mcp add -t http church-latin "https://churchlatin.ai/mcp" --header "X-Api-Key: YOUR_API_KEY"

Codex CLI (OpenAI)

Run once in your terminal (the key is read from the environment variable at startup):

codex mcp add church-latin --url "https://churchlatin.ai/mcp" --bearer-token-env-var CHURCH_LATIN_KEY

Then add your key to your shell profile: export CHURCH_LATIN_KEY="YOUR_API_KEY"

Claude Desktop, Cursor, Windsurf & others

Paste this into your MCP config file and replace YOUR_API_KEY:

{ "mcpServers": { "church-latin": { "type": "http", "url": "https://churchlatin.ai/mcp", "headers": { "X-Api-Key": "YOUR_API_KEY" } } } }
Claude Desktop~/Library/Application Support/Claude/claude_desktop_config.json (Mac)  /  %APPDATA%\Claude\claude_desktop_config.json (Windows)
Cursor.cursor/mcp.json in your project folder
Windsurf~/.codeium/windsurf/mcp_config.json

The server accepts your API key as either an X-Api-Key header or an Authorization: Bearer token — use whichever your client supports.

Your first request

Once connected, paste this into your AI assistant to confirm everything is working:

Use the church-latin MCP server to expand the abbreviations in this text and convert the date: "Obiit R.P. Joannes Brady, die XV Martii MDCCCCXX."

You should see the AI call expand_clerical_titles and convert_ecclesiastical_date in sequence, then give you a structured result. If you see a 401 error, your API key is missing from the config. If the server is unreachable, restart your AI client after adding the config.

Questions

What kinds of documents does this work with?

The tools are optimised for Catholic ecclesiastical Latin — necrologies, chapter acts, episcopal letters, professions of faith, charters, and similar records from religious orders and diocesan archives. They work best with 16th–20th century Latin, though date and place tools handle medieval documents too.

Which AI clients are compatible?

Any client that supports the Model Context Protocol (MCP) with HTTP transport: Claude Code (CLI), Claude Desktop, Codex CLI (OpenAI), Cursor, Windsurf, and others. The server follows the MCP standard and requires no special configuration beyond the endpoint URL and your API key.

Are my documents stored or logged?

No document text is stored. The server processes each request in memory and returns a result. The only data retained is your account record (email, plan, and API key) for billing and authentication.

Can I switch plans or cancel?

Yes — manage your subscription at any time through the Stripe customer portal. Cancellation takes effect at the end of the current billing period.

Will this translate my documents, or only extract metadata?

Both. Your AI assistant handles translation using its own language capabilities — Church Latin AI adds specialised tools on top: accurate date conversion, toponym resolution, abbreviation expansion, scripture identification, and structured metadata extraction. Think of it as giving your AI assistant a set of expert reference tools it can call on demand.

Do I need to know how to use Claude or Codex?

You need a working installation of one supported AI assistant (Claude Code, Claude Desktop, Codex CLI, Cursor, or Windsurf) and your Church Latin AI API key. Once configured, you simply describe what you want in plain English — the AI decides which tools to call. No programming required.

Can I try it without installing anything?

The free tier gives you 50 tool calls per month with no credit card required. You will need at least one MCP-compatible AI client installed — Claude Desktop is the easiest starting point for non-technical users. Download Claude Desktop here.

Is my archive's restricted or sensitive material safe?

Document text is never stored on this server — each request is processed in memory and discarded. However, text you paste into your AI assistant is processed by that assistant's provider (Anthropic for Claude, OpenAI for Codex, etc.) under their own privacy policies. For restricted or confidential records, check your AI provider's data handling terms before use. A self-hosted option for institutions with strict data governance requirements is on the roadmap.

What happens if the tool gives a wrong result?

All extraction tools include a requires_human_review flag and confidence ratings. Date conversions are cross-checked against age and profession-year formulas where possible. The tools are designed as a first-pass accelerator, not a replacement for archival judgement — every result should be verified before entering a catalogue.

Who built this, and why should I trust it?

Church Latin AI is built by Boyne Archives, an Irish archival services company with active contracts cataloguing the records of Catholic religious orders and dioceses. The tools are used in live archival work — not built speculatively. The ecclesiastical gazetteer, abbreviation lists, and date conversion rules are drawn from primary archival sources and tested against real documents.

Does it work with poor OCR or messy manuscript transcriptions?

Reasonably well. The normalisation tool corrects common OCR errors (u/v, i/j, ligatures) before other tools run. Abbreviation expansion and toponym lookup work on partial or inconsistently spelled text. Very poor quality OCR — garbled words, broken line endings, missing characters — will reduce accuracy and trigger human-review flags.

Can I export results directly to AtoM, ArchivesSpace, or Excel?

AtoM CSV (44-column ISAD(G) format), Dublin Core, EAD 2002 XML, and JSON are all supported export formats on the Professional and Team plans. The CSV can be imported directly into AtoM. For ArchivesSpace, use the JSON output and map fields to your import template. Excel can open any CSV export directly.

What counts as a tool call? Does batch triage count as one call or many?

Each tool invocation counts as one call, regardless of how many documents it processes. Sending 50 documents to the batch triage tool uses 1 call from your monthly allowance, not 50.

What happens when I reach my monthly limit?

Tool calls return a 401 response and your AI assistant will report that the server rejected the request. Your limit resets on the first of each month. You can check your current usage at any time: https://churchlatin.ai/usage?key=YOUR_API_KEY

I need a higher volume or a custom arrangement.

Contact info@archiveshosting.com to discuss annual contracts, pilot projects, or custom volume for larger institutions.