# Arg2P

Arg2P evaluates structured argumentation theories using ASPIC+ and ABA models directly within AI coding assistants.

- MCP server · `type=mcp` · Claude Code, Codex, Cursor, GitHub Copilot, Windsurf (Devin Desktop), Cline, Zed, Gemini CLI · ★ 16 repo stars
- Author: tuProlog
- License: MIT · policy=link-only · description only; the file stays with the author
- Source: https://github.com/tuProlog/arg2p-kt
- Updated: 2026-10-29
- Security check: automated, 2026-11-16 (text) — no signs of malicious code found.
- HTML: https://affpapa.org/en/nevibecode/mcp/arg2p

## What it does

Arg2P exposes the tuProlog argumentation engine to AI agents via the Model Context Protocol. It evaluates structured logic graphs, handles assumption-based argumentation, and resolves abstract dispute frameworks.

The MCP integration runs via `uvx arg2p`. Because the PyPI package bundles its own Java runtime environment, you do not need to configure an external JVM beforehand.

## Requirements
- Needs: Python and uv (commands run via uvx)

## Install

### Claude Code (native platform)

**Platform CLI**
```bash
claude mcp add arg2p -- uvx arg2p
```
uvx runs the command named after the package; if the README names another one, use uvx --from arg2p <command>

### Codex

**Platform CLI**
```bash
codex mcp add arg2p -- uvx arg2p
```
uvx runs the command named after the package; if the README names another one, use uvx --from arg2p <command>

### Cursor

**Config file**
File `.cursor/mcp.json`:
```json
{
    "mcpServers": {
        "arg2p": {
            "command": "uvx",
            "args": [
                "arg2p"
            ]
        }
    }
}
```
uvx runs the command named after the package; if the README names another one, use uvx --from arg2p <command>

### GitHub Copilot

**Config file**
File `.vscode/mcp.json`:
```json
{
    "servers": {
        "arg2p": {
            "type": "stdio",
            "command": "uvx",
            "args": [
                "arg2p"
            ]
        }
    }
}
```
uvx runs the command named after the package; if the README names another one, use uvx --from arg2p <command>

### Gemini CLI

**Platform CLI**
```bash
gemini mcp add arg2p uvx arg2p
```
uvx runs the command named after the package; if the README names another one, use uvx --from arg2p <command>

## When to use it
- solve structured argumentation frameworks under ASPIC+
- evaluate assumption-based ABA theories
- analyze conflict resolution in abstract argumentation graphs
- inspect formal debate outcomes directly in agent conversations

## Example prompts
- Evaluate this ASPIC+ argumentation framework and find the winning arguments
- Solve the following assumption-based argumentation theory using Arg2P
- Check which conclusions hold given these strict and defeasible rules

## Similar
- [debate-practice-coach](https://affpapa.org/en/nevibecode/skills/debate-practice-coach.md) — skill · 157 installs
- [proof-theory](https://affpapa.org/en/nevibecode/skills/proof-theory.md) — skill · 1 install
- [Prolog Reasoner](https://affpapa.org/en/nevibecode/mcp/prolog-reasoner.md) — MCP server · ★ 12 repo stars
- [propositional-logic](https://affpapa.org/en/nevibecode/skills/propositional-logic.md) — skill · 1 install
- [kibi-mcp](https://affpapa.org/en/nevibecode/mcp/kibi-mcp.md) — MCP server · ★ 13 repo stars
- [Euclid-MCP](https://affpapa.org/en/nevibecode/mcp/euclid-mcp.md) — MCP server · ★ 9 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
