Publifye MCP servers

Ten MCP servers from Publifye AS, a publishing house in Oslo. Connect them to Claude, Cursor, VS Code or any other MCP client and your assistant can study the Bible in Hebrew and Greek, write and publish a book, keep a dictionary, look up Norwegian companies and laws, check exchange rates, make PDFs, plan meetings, play the Bible aloud and keep your CV. They all run on our servers, so there is nothing to install.

Quickstart — connect in under a minute

Paste this into your MCP client's config and restart it. Sign-in happens in the browser on first use: OAuth 2.1 with PKCE and open Dynamic Client Registration, so there is no key to create first and nothing to install.

{
  "mcpServers": {
    "darash":  { "type": "http", "url": "https://darash-api.publifye.com/mcp" },
    "junifye": { "type": "http", "url": "https://junifye.publifye.com/mcp" },
    "lexifye": { "type": "http", "url": "https://lexifye.publifye.com/mcp" },
    "brreg":   { "type": "http", "url": "https://brreg.publifye.com/mcp" },
    "lexar":   { "type": "http", "url": "https://lexar-api.publifye.com/mcp" },
    "currency":{ "type": "http", "url": "https://currency.publifye.com/mcp" },
    "doksi":   { "type": "http", "url": "https://doksi.publifye.com/mcp" },
    "timely":  { "type": "http", "url": "https://timely.publifye.com/mcp" },
    "audiobible": { "type": "http", "url": "https://audiobible.publifye.com/mcp" },
    "vitae":      { "type": "http", "url": "https://vitae.publifye.com/mcp" }
  }
}

Take only the lines you want — each server stands alone.

• Claude Desktop — claude_desktop_config.json, or add each URL under Settings → Connectors.
• Claude Code — claude mcp add --transport http darash https://darash-api.publifye.com/mcp
• Cursor / VS Code — the same mcpServers block in the client's MCP settings file.

Prefer a key to a browser flow? Every endpoint also takes X-API-Key. Both routes, and the full OAuth discovery chain, are in docs/connect.md.

This repository is the canonical public reference for those servers: their endpoints, their complete tool schemas, and the provenance of every dataset behind them. It contains no server code — the services are hosted and commercial. What it contains is everything you need to evaluate them before you pay for anything.

Transport is Streamable HTTP throughout. Authentication is OAuth 2.1 with PKCE (S256) and Dynamic Client Registration, or a personal API key — except Brreg, which is OAuth only. See docs/connect.md.

Darash — the Hebrew and Greek text, as data

Most Bible tools give a model an English verse. Darash gives it the underlying data: which Hebrew stem a verb is in, which Strong's numbers actually occur in a given verse, what a 19th-century lexicon says about a lemma and which print edition that lexicon came from.

Measured on the live service, 2026-09-13:

Every one of those figures comes from the service's own get_health, not from a brochure. Regenerate them yourself once you have a key.

Why a translation is not enough. A Greek verb in the active voice can be rendered perfectly naturally in the passive in English. An argument about who is acting on whom, built on that English passive, is an argument about the translator. get_morphology returns the voice, person and stem the text actually carries, and strongs_in_verse proves a lemma is really in the verse rather than merely nearby in a concordance.

→ services/darash · tool schemas · PROVENANCE.md — read this one first if you are evaluating the data

Junifye — write the book, then publish it

Chapter-structured authoring over MCP: blocks, headings, Scripture quotations that resolve against a real Bible rather than the model's memory, tables, figures, footnote-free typesetting. Output is a print-ready PDF with the correct binding gutter, screen-reading PDFs, a valid EPUB3 and a web reader. Right-to-left scripts are supported end to end, and editions can be linked as translations of one another.

→ services/junifye · tool schemas

Lexifye — dictionaries with versions and sources

Entries, senses, per-definition sources, revision history and restore. Built for terminology work that has to be defensible later: every definition can carry where it came from, and every change is recoverable.

→ services/lexifye · tool schemas

Brreg — Norwegian organisations, by number or by name

Lookup by organisasjonsnummer, filtered search, and organisational structure over Brønnøysundregistrene's Enhetsregisteret, with key financials from Regnskapsregisteret fetched only when a call asks for them. A name returns candidates, never a silent pick. Open data under NLOD 2.0, attributed in every successful result; not the authoritative register, no roles or persons, no bulk export.

→ services/brreg · tool schemas · PROVENANCE.md · DATA-HANDLING.md

Lexar — the current text of Norwegian law

6,859 documents from Lovdata: 759 consolidated statutes, 5,112 central regulations and the current year's Norsk Lovtidend announcements, with the citation and source URL attached to every passage. Seven tools, and the number is fixed by specification rather than by what got built — richer capability goes into typed results, not more tools. resolve returns candidates and never picks a statute silently.

It is equally explicit about what it does not hold: no court decisions, no preparatory works, no local regulations, no historical consolidated versions. A search returning nothing does not mean there is no law. Open data under NLOD 2.0. Source text and navigation, not legal advice.

→ services/lexar · tool schemas · PROVENANCE.md — including the measured cross-reference miss rate

Currency — a published rate, or nothing

Norges Bank's daily reference rates: 38 currencies against NOK, back to about 1980, plus conversion and a daily series for charting. The discipline is in what it refuses to do — it never computes, estimates or interpolates a rate. Norges Bank publishes once per business day, so weekends and holidays have no rate, and those days come back as published rather than carried forward. A model that wants a number for a Sunday has to decide that for itself, which is where the decision belongs.

Two further tools price one USD list price into many markets from World Bank GNI per capita (PPP), and they return two numbers on purpose: factor, the recommended multiplier, never above 1.0; and raw_factor, the uncapped measurement, which exceeds 1.0 for countries richer than the United States. Norway measures about 1.10 — so applying the raw number to a Norwegian price charges above list, which is exactly what the cap exists to prevent.

→ services/currency · tool schemas

Doksi — ask what a kind requires, then write it