# Protologue

Connect an agent to a sourced taxonomy of prompting and LLM techniques. Use it to look up a method, see how terms relate, and find primary sources.

- MCP server · `type=mcp` · Claude Code, Codex, Cursor, GitHub Copilot, Windsurf (Devin Desktop), Cline, Zed, Gemini CLI
- Author: protologue-org
- License: not stated · policy=link-only · description only; the file stays with the author
- Source: https://github.com/protologue-org/protologue/tree/HEAD/mcp
- Updated: 2026-10-20
- HTML: https://affpapa.org/en/nevibecode/mcp/protologue

## What it does

Protologue is a reference taxonomy for prompting and LLM techniques. Its entries provide standalone definitions, alternate names, links between concepts, and primary sources. The MCP server makes this reference available to Claude Code, Codex, Cursor, and the other listed platforms.

The server runs as a Cloudflare Worker at `https://mcp.protologue.com/mcp`. Ask an agent to explain a technique, trace its links to related terms, or identify its sources. Benchmark entries cover what a benchmark measures, its scoring setup, and its limitations; they leave out scores and rankings. For Codex, connect it with `codex mcp add mcp --url https://mcp.protologue.com/mcp`.

## Requirements
- Remote server: `https://mcp.protologue.com/mcp`

## Install

### Claude Code (native platform)

**Platform CLI: remote server**
```bash
claude mcp add --transport http protologue https://mcp.protologue.com/mcp
```

### Codex

**Platform CLI: remote server**
```bash
codex mcp add mcp --url https://mcp.protologue.com/mcp
```

### Cursor

**Config file**
File `.cursor/mcp.json`:
```json
{
    "mcpServers": {
        "mcp": {
            "url": "https://mcp.protologue.com/mcp"
        }
    }
}
```

### GitHub Copilot

**Config file**
File `.vscode/mcp.json`:
```json
{
    "servers": {
        "mcp": {
            "type": "http",
            "url": "https://mcp.protologue.com/mcp"
        }
    }
}
```

### Gemini CLI

**Platform CLI: remote server**
```bash
gemini mcp add -t http mcp https://mcp.protologue.com/mcp
```

## When to use it
- look up a prompting technique’s definition
- trace links between LLM methods
- find primary sources for a term
- check what a benchmark measures and where its limits lie

## Example prompts
- Find the definition of self-consistency and list its primary sources.
- Explain how chain-of-thought relates to other techniques.
- What does this benchmark measure, and what limitations does its entry describe?

## Similar
- [MCP Toolbox for Databases](https://affpapa.org/en/nevibecode/mcp/googleapis-mcp-toolbox-for-databases.md) — MCP server · ★ 16741
- [labelhead-artist-momentum](https://affpapa.org/en/nevibecode/mcp/labelhead-artist-momentum.md) — MCP server · ★ 108044
- [Agent Skills Search Server](https://affpapa.org/en/nevibecode/mcp/agent-skills-search-server.md) — MCP server · ★ 26711
- [Skyvern](https://affpapa.org/en/nevibecode/mcp/skyvern.md) — MCP server · ★ 23288
- [Nhost](https://affpapa.org/en/nevibecode/mcp/nhost.md) — MCP server · ★ 9370
- [PraisonAI](https://affpapa.org/en/nevibecode/mcp/praisonai.md) — MCP server · ★ 9301

---
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