Urantia Papers is a remote MCP server that gives an AI agent 19 tools, among them audio.get, bible.book, bible.books. It answers at https://api.urantia.dev/mcp over streamable HTTP, and it listed its tools to an anonymous client, so no sign-in was needed for that. Our probes reached it 10 of 10 times since 5 September 2026; the last check, on 18 October 2026, succeeded.
The Urantia Papers in English and Spanish, with cross-references to the Bible and 21 texts. No key.
Description as the publisher wrote it.
| Tool | What it does |
|---|---|
audio.get | Get the audio file URL for a specific paragraph. Accepts any paragraph reference format (globalId "1:2.0.1", standardReferenceId "2:0.1", or paperSectionParagraphId "2.0.1"). Inputs: paragraph_ref |
bible.book | Get metadata for a single Bible book including chapter and verse counts. Accepts OSIS codes ("Gen"), USFM codes ("GEN"), full names ("Genesis"), and aliases ("genesis", "1-maccabees") — case-insensitive, hyphens/underscores tolerated. Inputs: book_code |
bible.books | List all 81 books of the World English Bible (eng-web): 39 Old Testament + 15 deuterocanonical + 27 New Testament. Each entry includes OSIS book code, full name, abbreviation, canonical order, canon, and chapter/verse counts. |
bible.chapter | Get every verse in a Bible chapter, ordered by verse number. Accepts OSIS, USFM, full name, or alias for `book_code`. Inputs: book_code, chapter |
bible.search.semantic | Free-form natural-language search across all Bible chunks, ranked by cosine similarity. Each result includes the top-N pre-computed Urantia paragraphs related to that chunk via `bible_parallels` (direction=bible_to_ub). One query surfaces b Inputs: query, q, canon, book_code, page, limit |
bible.verse | Get a single verse from the World English Bible (eng-web). Accepts OSIS, USFM, full name, or alias for `book_code`. Inputs: book_code, chapter, verse |
bible.verse.urantia_parallels | Returns the top 10 Urantia paragraphs whose embeddings are nearest to the Bible chunk that contains this verse — the reverse of `include_bible_parallels` on the UB side. Pre-computed at seed time with text-embedding-3-large (3072-d) cosine Inputs: book_code, chapter, verse |
entities.get | Get detailed information about a specific entity by its slug ID. Returns name, type, aliases, description, related entities, and citation count. Inputs: entity_id |
entities.list | Browse the entity catalog: beings, places, orders, races, religions, and concepts mentioned in the Urantia Book. Supports filtering by type and searching by name. Inputs: type, query, q, page, limit |
entities.paragraphs | Get all paragraphs that mention a specific entity, ordered by position in the text. Useful for studying everything said about a particular being, place, or concept. Inputs: entity_id, page, limit |
papers.get | Get a single paper with all its paragraphs. Paper IDs range from 0 (Foreword) to 196. Optionally include entity mentions. Inputs: paper_id, include_entities |
papers.list | List all 197 papers in the Urantia Book with their metadata (id, title, partId, labels). Use toc.get for a hierarchical view instead. |
papers.sections | Get all sections within a paper, ordered by section number. Useful for understanding paper structure before reading specific sections. Inputs: paper_id |
paragraphs.context | Get a paragraph with surrounding context (N paragraphs before and after within the same paper). Useful for understanding passages in context. Inputs: ref, window, include_entities |
paragraphs.get | Look up a specific paragraph by reference. Supports three formats: globalId ("1:2.0.1"), standardReferenceId ("2:0.1"), or paperSectionParagraphId ("2.0.1"). The format is auto-detected. Inputs: ref, include_entities, include_bible_parallels, include_urantia_parallels |
paragraphs.random | Get a random paragraph from the Urantia Book. Great for daily quotes, exploration, or discovering new passages. Inputs: include_entities, include_bible_parallels, include_urantia_parallels |
search.fulltext | Full-text search across all Urantia Book paragraphs. Supports three modes: "and" (all words must appear, default), "or" (any word), "phrase" (exact phrase). Results ranked by relevance. Inputs: query, q, type, paper_id, part_id, page |
search.semantic | Search the Urantia Book using semantic similarity (vector embeddings). Returns conceptually related results even without exact keyword matches. Requires OPENAI_API_KEY. Inputs: query, q, paper_id, part_id, page, limit |
toc.get | Get the full table of contents of the Urantia Book. Returns all 4 parts and 197 papers with their titles. This is the best starting point to understand the book structure. |
Every block below points at https://api.urantia.dev/mcp. Pick your client and copy.
claude mcp add --transport http urantia-papers https://api.urantia.dev/mcp
{
"mcpServers": {
"urantia-papers": {
"command": "npx",
"args": ["-y", "mcp-remote", "https://api.urantia.dev/mcp"]
}
}
}{
"mcpServers": {
"urantia-papers": {
"url": "https://api.urantia.dev/mcp"
}
}
}{
"servers": {
"urantia-papers": {
"type": "http",
"url": "https://api.urantia.dev/mcp"
}
}
}{
"context_servers": {
"urantia-papers": {
"url": "https://api.urantia.dev/mcp"
}
}
}{
"mcpServers": {
"urantia-papers": {
"serverUrl": "https://api.urantia.dev/mcp"
}
}
}{
"mcpServers": {
"urantia-papers": {
"url": "https://api.urantia.dev/mcp"
}
}
}name: Urantia Papers
version: 0.0.1
schema: v1
mcpServers:
- name: Urantia Papers
type: streamable-http
url: https://api.urantia.dev/mcp{
"mcpServers": {
"urantia-papers": {
"httpUrl": "https://api.urantia.dev/mcp"
}
}
}{
"mcpServers": {
"urantia-papers": {
"type": "http",
"url": "https://api.urantia.dev/mcp"
}
}
}{
"mcpServers": {
"urantia-papers": {
"url": "https://api.urantia.dev/mcp"
}
}
}goose://extension?url=https%3A%2F%2Fapi.urantia.dev%2Fmcp&type=streamable_http&id=urantia-papers&name=Urantia%20Papers
It answered our last check on 18 October 2026 in 499 ms. Over 10 checks since 5 September 2026 it answered 10. Status here comes from Neuronto's own probes, not from the publisher.
Yes. It is published by urantia.dev and served from api.urantia.dev, the vendor's own domain: https://api.urantia.dev/mcp.
19, as returned by the server's own tools/list on 31 August 2026: audio.get, bible.book, bible.books, bible.chapter, bible.search.semantic, bible.verse, bible.verse.urantia_parallels, entities.get, and 11 more.
It answered our last check on 18 October 2026 in 499 ms. Over 10 checks since 5 September 2026 it answered 10.
Put the server under mcpServers in ~/.cursor/mcp.json with the URL https://api.urantia.dev/mcp. The exact JSON is above, with the same setup for Claude Code, Claude Desktop, VS Code, Windsurf, Zed, Gemini CLI and the rest.
It listed its tools to an anonymous client, so reading the tool list needs no key. Individual tools can still ask for credentials in their own inputs.
Publisher: dev.urantia. Endpoint host: api.urantia.dev. ARD identifier: urn:air:dev.urantia:mcp:urantia-papers.
First indexed 31 August 2026. The tools are exactly what the server returned; nothing on this page
is inferred from its name. Ranking in Neuronto search is never for sale.