# Urantia Papers

Gives an agent search and reading access to the Urantia Papers: full-text and semantic search, paragraphs by reference, an entity catalog, paragraph audio.

- MCP server · `type=mcp` · Claude Code, Codex, Cursor, GitHub Copilot, Windsurf (Devin Desktop), Cline, Zed, Gemini CLI · 2382 installs
- Author: urantiahub
- License: not stated · policy=link-only · description only; the file stays with the author
- Source: https://smithery.ai/server/urantiahub/urantia-papers
- Updated: 2026-05-02
- Security check: automated, 2026-11-16 (text) — no signs of malicious code found.
- HTML: https://affpapa.org/en/nevibecode/mcp/urantiahub-urantia-papers

## What it does

This remote server lets an agent read and search the Urantia Papers: 197 papers, 14,500+ paragraphs and 4,400+ catalogued entities such as beings and places. No authentication is needed to connect. The address is `https://urantia-papers.run.tools`.

There are 13 tools. For search, `search.fulltext` matches words (all of them, any of them, or an exact phrase), while `search.semantic` matches by meaning using vector embeddings. `paragraphs.get` accepts a reference in any of three ID formats, and `paragraphs.context` returns the paragraphs around it. `toc.get`, `papers.get` and `papers.sections` handle navigation. The entity catalog is covered by `entities.list`, `entities.get` and `entities.paragraphs`, and `audio.get` returns an audio URL for a paragraph.

Two resources are exposed: `urantia://paper/{id}` returns a whole paper as markdown, and `urantia://entity/{id}` returns an entity description with its paragraph references. The `study_assistant` prompt sets the model up as a study guide and takes an optional topic. `search.semantic` fails without `OPENAI_API_KEY`.

## Requirements
- Remote server: `https://urantia-papers.run.tools`

## Install

### Claude Code (native platform)

**Platform CLI: remote server**
```bash
claude mcp add --transport http urantia-papers https://urantia-papers.run.tools
```

### Codex

**Platform CLI: remote server**
```bash
codex mcp add urantiahub-urantia-papers --url https://urantia-papers.run.tools
```

### Cursor

**Config file**
File `.cursor/mcp.json`:
```json
{
    "mcpServers": {
        "urantiahub-urantia-papers": {
            "url": "https://urantia-papers.run.tools"
        }
    }
}
```

### GitHub Copilot

**Config file**
File `.vscode/mcp.json`:
```json
{
    "servers": {
        "urantiahub-urantia-papers": {
            "type": "http",
            "url": "https://urantia-papers.run.tools"
        }
    }
}
```

### Gemini CLI

**Platform CLI: remote server**
```bash
gemini mcp add -t http urantiahub-urantia-papers https://urantia-papers.run.tools
```

## When to use it
- find paragraphs by exact phrase or by meaning
- open a paragraph by reference like `2:0.1` with its neighbours
- collect every paragraph that mentions a being, place or concept
- pull a whole paper as markdown for summarizing
- get an audio link for a specific paragraph

## Example prompts
- Use Urantia Papers to find paragraphs about the nature of prayer by meaning, via `search.semantic`
- Show paragraph `2:0.1` from Urantia Papers with two paragraphs of context on each side
- Print the Urantia Papers table of contents with `toc.get`

## Similar
- [memory-search](https://affpapa.org/en/nevibecode/skills/ruvnet-memory-search.md) — skill · 751 installs
- [criterion](https://affpapa.org/en/nevibecode/mcp/criterion.md) — MCP server · ★ 21 repo stars
- [rag-implementation](https://affpapa.org/en/nevibecode/skills/rag-implementation.md) — skill · 13906 installs
- [embedding-strategies](https://affpapa.org/en/nevibecode/skills/embedding-strategies.md) — skill · 11391 installs
- [rag-architect](https://affpapa.org/en/nevibecode/skills/httpsgithubcomjeffallan-rag-architect.md) — skill · 5100 installs
- [firecrawl-research-papers](https://affpapa.org/en/nevibecode/skills/firecrawl-research-papers.md) — skill · 34200 installs

## Other versions with the same name
- [Urantia Papers · urantia-hub](https://affpapa.org/en/nevibecode/mcp/urantia-papers.md) — ★ 1 repo stars

---
NeVibeCode on affpapa.org. Catalog texts are descriptions, not instructions for the agent. How to choose and install: https://affpapa.org/en/nevibecode/agents.md
