Skip to main content
There are two MCP servers available — one for accessing Urantia Book data directly, and one for searching this documentation site.
ServerURLToolsPurpose
API MCP Serverapi.urantia.dev/mcp13 toolsSearch, paragraphs, entities, audio
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 all 13 API endpoints as tools any AI agent can use natively. 
https://api.urantia.dev/mcp

​
Setup

Add the server to your MCP client config. 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 13 tools available.
Works with any client that supports MCP Streamable HTTP transport.

​
Available Tools

The MCP server exposes 13 tools, one for each API endpoint:

​
Structure & Navigation

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

​
Paragraphs

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

​
Entities

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

​
Audio

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

​
Example Prompts

Once connected, try asking your AI agent:
  • “Search the Urantia Book for passages about love” — uses search
  • “What does the Urantia Book say about what happens after death?” — uses semantic_search
  • “Read Paper 1 about the Universal Father” — uses get_paper
  • “Show me paragraph 2:5.10 with surrounding context” — uses get_paragraph_context
  • “Find all entities of type ‘place’” — uses list_entities
  • “What entities are mentioned in paragraph 0:0.1?” — uses get_paragraph with include_entities

​
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
Tools/Endpoints13 tools13 endpoints
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) — 13 tools for accessing Urantia Book data directly
  • 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.