Skip to content
MCP server

Arg2P

Solve ASPIC+, ABA and abstract argumentation theories from an AI assistant

Runs locallyStatus and history
Pricing
Open source
Platforms
Web, vscode, CLI
Runs
Locally
Version
0.26.7
Listing updated
3 days ago

About Arg2P

Arg2P is an open-source MCP server for developer tools. It runs locally on your machine and is started by your AI client.

Arg2P is a structured-argumentation solver built on the tuProlog engine. Its language server doubles as an MCP server, so an assistant can load a theory, solve it and explore the results instead of reasoning about attacks and defeats by hand.

The solver reads ASPIC+ theories as well as assumption-based and abstract frameworks, and the same API runs on the JVM, in JavaScript and in Python. The MCP server is published on PyPI as arg2p and runs over stdio; the pip wheel bundles a Java runtime.

The project also offers a browser playground that draws the argument graph of each solution, a VS Code extension for .arg2p files, and plugins for Claude Code and Codex. It is described in a peer-reviewed paper in the Journal of Logic and Computation, which makes it a fit for research and legal-reasoning work.

Install

Run in a terminal

claude mcp add arg2p -- uvx arg2p

Add to claude_desktop_config.json

{
  "mcpServers": {
    "arg2p": {
      "command": "uvx",
      "args": [
        "arg2p"
      ]
    }
  }
}
Install in CursorOpens Cursor, which asks you to confirm. Or add it by hand:

Add to ~/.cursor/mcp.json

{
  "mcpServers": {
    "arg2p": {
      "command": "uvx",
      "args": [
        "arg2p"
      ]
    }
  }
}
Install in VS CodeOpens VS Code, which asks you to confirm. Or add it by hand:

Add to .vscode/mcp.json

{
  "servers": {
    "arg2p": {
      "type": "stdio",
      "command": "uvx",
      "args": [
        "arg2p"
      ]
    }
  }
}

Add to ~/.codeium/windsurf/mcp_config.json

{
  "mcpServers": {
    "arg2p": {
      "command": "uvx",
      "args": [
        "arg2p"
      ]
    }
  }
}

Add to your client's MCP settings (most use this shape)

{
  "mcpServers": {
    "arg2p": {
      "command": "uvx",
      "args": [
        "arg2p"
      ]
    }
  }
}

What it does

Three framework types
Solves ASPIC+, assumption-based (ABA) and abstract argumentation theories.
Explorable results
Lets an assistant walk through solutions one at a time and inspect their graphs.
Cross-platform engine
Same API on the JVM, JavaScript (Node.js and browsers) and Python.
Web playground
Runs the solver in the browser and imports APX, TGF and ICCMA'23 files.
VS Code extension
Highlights `.arg2p` theories and shows syntax errors as you type.
Assistant plugins
Install paths for Claude Code and Codex alongside the standalone MCP server.

Good for

  • Let an assistant check whether an argument survives its attackers
  • Evaluate legal or normative reasoning encoded as ASPIC+ rules
  • Teach or prototype argumentation semantics without writing a solver
  • Convert and inspect abstract frameworks from APX or TGF files

Pricing

Open source

Free to install from PyPI, npm and Maven Central

Prices change. Check tuprolog.github.io before you buy.

Arg2P FAQ

How do I install the MCP server?

It is on PyPI as `arg2p` (`pip install arg2p`); the wheel bundles a Java runtime.

Can I try it without installing?

Yes, the Web Playground runs the solver in the browser.

Which frameworks does it understand?

ASPIC+, assumption-based and abstract argumentation frameworks.

Is Arg2P free?

Yes. Arg2P is open source, so you can use and self-host it for free.

How do I add Arg2P to Claude Code?

Run this command in your terminal: claude mcp add arg2p -- uvx arg2p

What are the best alternatives to Arg2P?

The closest alternatives to Arg2P are REA, Codebase Memory, GitHub, Serena MCP: the IDE for your agent and XERJ.

Alternatives to Arg2P

  1. REA

    MCP server

    CLI and MCP server that lets coding agents reverse engineer apps and binaries

    Runs locally
    • Open source
    • 464K GitHub stars
    • Developer tools
  2. Codebase Memory

    MCP server

    Local MCP server that builds a code knowledge graph for AI coding agents

    Runs locally
    • Open source
    • 48.7K GitHub stars
    • Knowledge and memory
  3. GitHub

    MCP server

    Official MCP server connecting AI assistants to GitHub repos, issues and workflows

    Not checked yet
    • Remote
    • Open source
    • 34.5K GitHub stars
    • Developer tools
  4. MCP toolkit giving coding agents symbol-level code retrieval and editing

    Runs locally
    • Open source
    • 31.5K GitHub stars
    • Developer tools
  5. XERJ

    MCP server

    Local search engine for AI agents with cited answers over your code and docs

    Runs locally
    • Open source
    • 19.2K GitHub stars
    • Knowledge and memory
  6. Ouroboros

    MCP server

    Spec-first layer that pins requirements and verifies results of AI coding agent work

    Runs locally
    • Open source
    • 6.4K GitHub stars
    • Developer tools