Skip to main content

Documentation Index

Fetch the complete documentation index at: https://urantia.dev/llms.txt

Use this file to discover all available pages before exploring further.

There are two MCP servers available — one for accessing Urantia Book data directly, and one for searching this documentation site.
ServerURLCapabilitiesPurpose
API MCP Serverapi.urantia.dev/mcp19 tools, 2 resources, 2 promptsSearch, paragraphs, entities, audio, Bible (WEB) + UB↔Bible cross-references
Docs MCP Serverurantia.dev/mcp1 toolSearch the documentation site

API MCP Server

The Urantia Papers API includes a built-in Model Context Protocol (MCP) server that exposes API endpoints as tools, papers/entities as resources, and study workflows as prompts that any AI agent can use natively.
https://api.urantia.dev/mcp

Listed in the official registries

This server is published in the canonical registries that MCP-aware clients query for discovery:
  • MCP Registry (Anthropic-stewarded, official) — dev.urantia/urantia-papers. Verifiable: curl "https://registry.modelcontextprotocol.io/v0/servers?search=urantia"
  • Smithery — community marketplace with one-click install + 100/100 quality score
smithery badge

One-click install via Smithery

The fastest way to add this server to your MCP client is via Smithery — it generates the right config snippet for your client and handles the install.

Manual setup

Add the server to your MCP client config directly. No API key, no installation, no build step.
Add to ~/Library/Application Support/Claude/claude_desktop_config.json (macOS) or %APPDATA%\Claude\claude_desktop_config.json (Windows):
{
  "mcpServers": {
    "urantia-papers": {
      "url": "https://api.urantia.dev/mcp"
    }
  }
}
Restart Claude Desktop. You’ll see 19 tools available.
Works with any client that supports MCP Streamable HTTP transport.

Available Tools

The MCP server exposes 19 tools using dot-notation names organized into a navigable namespace tree. All tools advertise read-only annotations and ship with output schemas for structured responses.

Structure & Navigation

ToolDescription
toc.getGet the full table of contents — all 4 parts and 197 papers. Best starting point.
papers.listList all 197 papers with metadata (id, title, partId, labels).
papers.getGet a single paper with all its paragraphs. Supports include_entities.
papers.sectionsGet all sections within a paper, ordered by section number.

Paragraphs

ToolDescription
paragraphs.getLook up a paragraph by reference. Supports 3 formats: "1:2.0.1", "2:0.1", "2.0.1".
paragraphs.contextGet a paragraph with N paragraphs before and after (configurable window, 1-10).
paragraphs.randomGet a random paragraph. Great for exploration.
ToolDescription
search.fulltextFull-text search. Modes: and (default), or, phrase. Filters: paper_id, part_id.
search.semanticSemantic similarity search via vector embeddings. Finds conceptually related passages.

Entities

ToolDescription
entities.listBrowse 4,400+ entities (beings, places, orders, races, religions, concepts). Filter by type or search by q.
entities.getGet entity details: name, type, aliases, description, related entities, citation count.
entities.paragraphsGet all paragraphs that mention a specific entity.

Audio

ToolDescription
audio.getGet audio file URLs for a paragraph. Accepts any reference format.

Bible (World English Bible)

ToolDescription
bible.booksList all 81 books (39 OT + 15 deuterocanonical + 27 NT) with OSIS codes, canon, chapter counts.
bible.bookGet a single book’s metadata. Accepts OSIS, USFM, full names, and aliases (case-insensitive).
bible.chapterGet all verses in a chapter, ordered by verse number.
bible.verseGet a single verse by bookCode, chapter, verse.
bible.verse.urantia_parallelsReverse cross-reference — top-10 Urantia paragraphs semantically nearest a Bible verse.
bible.search.semanticLive semantic search over all 38,034 Bible verses; results arrive with their nearest UB paragraphs already attached.

Cross-reference enrichment on existing tools

paragraphs.get, paragraphs.random, search.fulltext, and search.semantic accept two optional booleans that attach pre-computed semantic neighbors to each result:
ParamWhat you get
include_bible_parallelsTop-10 Bible verses semantically nearest each UB paragraph.
include_urantia_parallelsTop-10 Urantia paragraphs semantically nearest each UB paragraph (UB ↔ UB “see also”).
Both can be combined. Parallels are pre-computed via text-embedding-3-large cosine similarity, so adding them is cheap. Note: these are semantic neighbors, not curated linguistic parallels (e.g. Faw’s Paramony) — best results trend conceptual rather than verse-citation.

Resources

In addition to tools, the server exposes two resource templates clients can read directly:
URI TemplateDescription
urantia://paper/{id}A single paper rendered as plaintext markdown with section headings and paragraph references. Useful for full-paper context in RAG or summarization.
urantia://entity/{id}An entity (being, place, order, race, religion, or concept) with description, aliases, related entities, and references to all paragraphs that mention it.

Prompts

The server also publishes two reusable prompt templates for common study workflows:
PromptArgumentsDescription
study_assistanttopic (optional)Primes the model to act as a Urantia Book study guide. Optionally focuses the session on a specific topic or passage.
comparative_theologytopic, traditionStructures a comparison between a Urantia Book teaching and another religious or philosophical tradition (e.g. Buddhism, Stoicism).

Example Prompts

Once connected, try asking your AI agent:
  • “Search the Urantia Book for passages about love” — uses search.fulltext
  • “What does the Urantia Book say about what happens after death?” — uses search.semantic
  • “Read Paper 1 about the Universal Father” — uses the urantia://paper/1 resource
  • “Show me paragraph 2:5.10 with surrounding context” — uses paragraphs.context
  • “Find all entities of type ‘place’” — uses entities.list
  • “What entities are mentioned in paragraph 0:0.1?” — uses paragraphs.get with include_entities
  • “Compare what the Urantia Book teaches about the soul with Stoic philosophy” — uses the comparative_theology prompt
  • “Find Urantia Book paragraphs related to Matthew 5:3” — uses bible.verse.urantia_parallels
  • “Search the Bible for passages about forgiveness and show the related Urantia teachings” — uses bible.search.semantic
  • “Show me 0:0.1 with both Bible parallels and related Urantia paragraphs” — uses paragraphs.get with include_bible_parallels and include_urantia_parallels

How It Works

The MCP server uses Streamable HTTP transport, which means:
  • No local process — it runs on the same Cloudflare Worker as the API
  • Stateless — each request creates a fresh server instance (no sessions to manage)
  • Same rate limits as the REST API (100 requests/minute per IP)
  • Same data — MCP tools query the database directly, returning the same results as the REST endpoints

MCP vs REST

Both give you access to the same data. Choose based on your use case:
MCP (api.urantia.dev/mcp)REST (api.urantia.dev/*)
Best forAI agents (Claude, Cursor, etc.)Apps, scripts, manual exploration
ProtocolJSON-RPC over Streamable HTTPStandard HTTP
AuthNoneNone
Surface19 tools, 2 resources, 2 promptsAll endpoints + /tools/openai, /tools/anthropic for SDK use
Response formatMCP content blocksJSON with data/meta wrappers

Docs MCP Server

Mintlify provides a hosted MCP server that lets AI agents search these documentation pages — useful for discovering endpoints, understanding usage patterns, and learning the API.
https://urantia.dev/mcp

Setup

Add to ~/Library/Application Support/Claude/claude_desktop_config.json (macOS) or %APPDATA%\Claude\claude_desktop_config.json (Windows):
{
  "mcpServers": {
    "urantia-dev-docs": {
      "command": "npx",
      "args": ["-y", "@anthropic-ai/mcp-remote@latest", "https://urantia.dev/mcp"]
    }
  }
}

Available Tool

ToolDescription
SearchUrantiaDevSearch across the documentation to find endpoint references, code examples, guides, and usage patterns.

Example Prompts

  • “How do I search the Urantia Papers API?”
  • “What paragraph reference formats does the API support?”
  • “Show me how to use the entities endpoint”
  • “What audio voices are available?”

Using Both MCP Servers

For the best experience, add both servers to your client:
{
  "mcpServers": {
    "urantia-papers": {
      "url": "https://api.urantia.dev/mcp"
    },
    "urantia-dev-docs": {
      "command": "npx",
      "args": ["-y", "@anthropic-ai/mcp-remote@latest", "https://urantia.dev/mcp"]
    }
  }
}
  • API MCP Server (api.urantia.dev/mcp) — 19 tools for accessing Urantia Book data, the World English Bible, and UB↔Bible cross-references
  • Docs MCP Server (urantia.dev/mcp) — 1 tool for searching this documentation site

Building a Custom MCP Server

If you need custom logic (e.g., combining multiple tools, caching, or preprocessing results), you can build your own MCP server that calls our REST API. See the Build an MCP Server tutorial for a step-by-step guide.