# Arg2P (pypi · arg2p)

Structured argumentation: solve ASPIC+, ABA and abstract theories, explore their results

- Trust score: 81/100 (high trust)
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-11-04

## Components

- pypi · `arg2p`: 81/100 (this document), [markdown](https://verifymcp.io/servers/tuprolog-arg2p/arg2p.md), [page](https://verifymcp.io/servers/tuprolog-arg2p/arg2p)

## Channel facts

- Registry: `pypi`
- Package: `arg2p`
- Version: `0.23.0`
- Transport: `stdio`

## Trust breakdown

How this component scores in each security and reliability category. Every signal is checked automatically from public evidence about the published package, including repeated runs of it in an isolated sandbox, and we only credit what we can confirm. Scores are 0–100 per category. Scoring method: https://verifymcp.io/docs/scoring (what has changed: https://verifymcp.io/docs/scoring/changelog)

Scored 2026-11-04.

- **Supply Chain Security**: 100/100
  - No malware found by supply-chain analysis.
  - No known CVEs affecting this package version or its production dependencies.
  - No install/post-install scripts declared.
  - 0 of 2 dependencies flagged as unhealthy.
- **Provenance & Transparency**: 97/100
  - Source repository is publicly reachable at the declared URL.
  - Cryptographically verified build provenance (signed, bound to tuProlog/arg2p-kt).
  - Clear OSI-approved license (MIT).
  - Actively maintained (last published 5 days ago).
  - Disclosure check failed: no security disclosure policy was found in the source repository.
- **Schema Quality & AI Usability**: 69/100
  - 100% of prompts and resources have a non-trivial description (not blank, and not just the item's name).
  - AI-judged instruction clarity (good).
  - Context-footprint check failed: tool/resource definitions use about 1759 tokens (~293/item across 6 items; 5 tools + 1 resources), over budget; trim descriptions and params.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 20/100
  - Stability observed for 6 of 30 days with no destabilising changes; credit accrues until the full window elapses.
- **Tool Coverage**: 100/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 100% of tool parameters carry a description.
- **Tool Safety**: 100/100
  - No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.
  - We read all 5 captured tool definition(s), and no name or description among them implies an irreversible operation.
  - An AI judge read all 7 captured unit(s) of tool text and found none that tries to manipulate the model reading it.
- **Capabilities**: 60/100
  - Spec-recency check failed: implements MCP spec 2025-06-18; the latest is 2026-07-28.

## Install

### How do I install the Arg2P MCP server?

Arg2P runs locally as a PyPI package, launched with uvx arg2p. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.

### Claude

```bash
claude mcp add tuprolog-arg2p -- uvx arg2p
```

### Cursor

```json
{
  "mcpServers": {
    "tuprolog-arg2p": {
      "command": "uvx",
      "args": [
        "arg2p"
      ]
    }
  }
}
```

### VS Code

```json
{
  "servers": {
    "tuprolog-arg2p": {
      "command": "uvx",
      "args": [
        "arg2p"
      ]
    }
  }
}
```

### Codex

```bash
codex mcp add tuprolog-arg2p -- uvx arg2p
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "tuprolog-arg2p": {
      "type": "local",
      "command": [
        "uvx",
        "arg2p"
      ],
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add tuprolog-arg2p --command uvx --arg arg2p
```

### Hermes

```yaml
mcp_servers:
  tuprolog-arg2p:
    command: "uvx"
    args: ["arg2p"]
```

### Netclaw

```json
{
  "McpServers": {
    "tuprolog-arg2p": {
      "Transport": "stdio",
      "Command": "uvx",
      "Arguments": [
        "arg2p"
      ]
    }
  }
}
```

### Vellum

```bash
assistant mcp add tuprolog-arg2p -t stdio -c uvx -a arg2p
```

### Other

```json
{
  "mcpServers": {
    "tuprolog-arg2p": {
      "command": "uvx",
      "args": [
        "arg2p"
      ]
    }
  }
}
```

## Changelog

Every change recorded for this component, newest first. Days that predate change tracking, or that we cannot explain, say so: "we were watching and nothing happened" and "we were not watching" are different claims.

### 2026-11-03 (score 81, +1)

No change was recorded against any check on this day. Stability & Change Management went from 13 to 17. That category is still filling its 30-day observation window: 4 days of observed history at the previous scan, 5 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-11-01 (score 80, +1)

No change was recorded against any check on this day. Stability & Change Management went from 7 to 10. That category is still filling its 30-day observation window: 2 days of observed history at the previous scan, 3 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-10-30 (score 79, +1)

No change was recorded against any check on this day. Stability & Change Management went from 0 to 3. That category is still filling its 30-day observation window: 0 days of observed history at the previous scan, 1 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-10-29 (score 78)

First indexed and scored.

## MCP tools (5)

### `solve` (~458 tokens)

Solve a query

Solves a query on a theory of arg2p: its first solutions (yes, no, or halt with an error), with their bindings, and the argument graph of the last yes (every argument with its conclusion, top rule, sub-arguments and label in, out or und; every attack with its type); more tells whether the search has alternatives left (they may give other solutions, or no). The default query, arg2p::solve(In, Out, Und), gives the statements labelled in, out and und. Out of time, it gives the solutions found until then (timedOut).

Input parameters:

- `flags` (string): The flags, as Prolog facts: argumentLabellingMode(grounded|complete|preferred|stable|semistable|ideal|eager|naive|stage|cf2|stage2|...), statementLabellingMode(statement), queryMode, graphBuildMode(.…
- `maxSolutions` (integer): How many solutions at most (default 5, at most 100)
- `query` (string): A Prolog goal on the theory (default: arg2p::solve(In, Out, Und))
- `theory` (string, required): The theory, in the language of arg2p: rules `r1 : bird(X) => flies(X).` (defeasible) and `r2 : a -> b.` (strict), premises `f1 :=> bird(tweety).`, axioms `f2 :-> a.`, preferences `sup(r1, r2).`, nega…
- `timeoutSeconds` (integer): How long to wait, in seconds (default 60, at most 600)

### `answer` (~350 tokens)

Label the statements of a query

The statements matching a query (a literal, as flies(X) or -flies(tweety)) labelled in (justified), out (rejected) and und (undecided) by the theory, under its semantics.

Input parameters:

- `flags` (string): The flags, as Prolog facts: argumentLabellingMode(grounded|complete|preferred|stable|semistable|ideal|eager|naive|stage|cf2|stage2|...), statementLabellingMode(statement), queryMode, graphBuildMode(.…
- `query` (string, required): A literal, as flies(tweety) or flies(X)
- `theory` (string, required): The theory, in the language of arg2p: rules `r1 : bird(X) => flies(X).` (defeasible) and `r2 : a -> b.` (strict), premises `f1 :=> bird(tweety).`, axioms `f2 :-> a.`, preferences `sup(r1, r2).`, nega…
- `timeoutSeconds` (integer): How long to wait, in seconds (default 60, at most 600)

### `check` (~54 tokens)

Check a theory or a query

Whether a theory (or flags) or a query parses, and where it does not (line, column, token).

Input parameters:

- `kind` (string): What the text is (default theory)
- `text` (string, required): The text

### `settings` (~332 tokens)

The settings in effect

The value in effect of every flag for a theory: its profile (graphBuildMode), the semantics, the graph extensions, ... as the theory, the flags and the profile set them. A theory that does not parse is refused.

Input parameters:

- `flags` (string): The flags, as Prolog facts: argumentLabellingMode(grounded|complete|preferred|stable|semistable|ideal|eager|naive|stage|cf2|stage2|...), statementLabellingMode(statement), queryMode, graphBuildMode(.…
- `theory` (string, required): The theory, in the language of arg2p: rules `r1 : bird(X) => flies(X).` (defeasible) and `r2 : a -> b.` (strict), premises `f1 :=> bird(tweety).`, axioms `f2 :-> a.`, preferences `sup(r1, r2).`, nega…
- `timeoutSeconds` (integer): How long to wait, in seconds (default 60, at most 600)

### `explore` (~396 tokens)

Show the solver of a theory

Shows the user the solver of a theory, to explore its results themselves: the query run, its solutions, the argument graph of each and the stages of its computation, the drawing of an abstract framework, the flags. Hosts of MCP Apps show it in the conversation; the result links the same theory in the web playground, for every host. Use it when the user wants to see or explore the results.

Input parameters:

- `flags` (string): The flags, as Prolog facts: argumentLabellingMode(grounded|complete|preferred|stable|semistable|ideal|eager|naive|stage|cf2|stage2|...), statementLabellingMode(statement), queryMode, graphBuildMode(.…
- `query` (string): The query run first (default: arg2p::solve(In, Out, Und))
- `theory` (string, required): The theory, in the language of arg2p: rules `r1 : bird(X) => flies(X).` (defeasible) and `r2 : a -> b.` (strict), premises `f1 :=> bird(tweety).`, axioms `f2 :-> a.`, preferences `sup(r1, r2).`, nega…
- `timeoutSeconds` (integer): How long each run of the solver shown waits, in seconds (default 60, at most 600)

## Diagnostics

Captured diagnostic sections: Provenance, Dependencies. The full working is on the page: https://verifymcp.io/servers/tuprolog-arg2p/arg2p#diagnostics

## Score history

- 2026-11-04: 81
- 2026-11-03: 81
- 2026-11-02: 80
- 2026-11-01: 80
- 2026-10-31: 79
- 2026-10-30: 79
- 2026-10-29: 78

## Common questions

### What is the Arg2P MCP server?

Arg2P is an MCP server listed in the public MCP registry as io.github.tuProlog/arg2p. Structured argumentation: solve ASPIC+, ABA and abstract theories, explore their results. This page covers its PyPI package (arg2p).

### Is the Arg2P MCP server safe to use?

Arg2P scores 81 out of 100 on VerifyMCP. We found no known CVEs affecting it as of 4 November 2026. It declares no install or post-install scripts. Its build provenance is signed and verified. That is a record of what we were able to check automatically, not an endorsement. The category breakdown on this page shows every signal behind the number, including the ones we could not confirm.

### What tools does the Arg2P MCP server expose?

Arg2P exposes 5 tools: solve, answer, check, settings, explore. Their descriptions and schemas cost roughly 1,590 tokens of context every time the server is loaded.

### Is the Arg2P MCP server still maintained?

Arg2P is still listed as active in the MCP registry. We last reached this channel on 4 November 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.

### What licence is the Arg2P MCP server under?

Arg2P declares the MIT licence, which is OSI-approved. That covers the source only, and says nothing about the cost of any service it calls.

## Links

- PyPI project: https://pypi.org/project/arg2p/
- Socket report: https://socket.dev/pypi/package/arg2p
- Repository: https://github.com/tuProlog/arg2p-kt
- Website: https://tuprolog.github.io/arg2p-kt/
- Changelog RSS feed: https://verifymcp.io/servers/tuprolog-arg2p/arg2p.xml
- Changelog JSON feed: https://verifymcp.io/servers/tuprolog-arg2p/arg2p.json
- HTML version of this page: https://verifymcp.io/servers/tuprolog-arg2p/arg2p