# RogueGPT (pypi · roguegpt)

Store and retrieve controlled AI news stimuli with generation metadata for misinformation research

- Trust score: 64/100 (medium)
- Change this week: −15
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-11-21

## Components

- pypi · `roguegpt`: 64/100 (this document), [markdown](https://verifymcp.io/servers/aloth-roguegpt/roguegpt.md), [page](https://verifymcp.io/servers/aloth-roguegpt/roguegpt)

## Channel facts

- Registry: `pypi`
- Package: `roguegpt`
- Version: `1.5.0`
- 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 2026-11-21.

- **Supply Chain Security**: 50/100
  - Malware scan not yet available for this package.
  - No known CVEs affecting this package version or its production dependencies.
  - Runs setuptools.build_meta at install time, a recognised build step with no custom scripting around it.
  - 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 aloth/RogueGPT).
  - Clear OSI-approved license (GPL-3.0-or-later).
  - Actively maintained (last published 13 days ago).
  - Disclosure check failed: no security disclosure policy was found in the source repository.
- **Schema Quality & AI Usability**: 75/100
  - 100% of prompts and resources have a non-trivial description (not blank, and not just the item's name).
  - AI-judged instruction clarity (fair).
  - Tool/resource definitions use about 449 tokens (~89/item across 5 items; 2 tools + 3 resources), lean.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 0/100
  - Stability not yet verified: not enough scan history yet (needs a 30-day window).
- **Tool Coverage**: 71/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 0% of tool parameters carry a description.
  - Structured output schemas are declared (100% of tools); any adoption earns full credit.
- **Tool Safety**: 100/100
  - No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.
  - We read all 2 captured tool definition(s), and no name or description among them implies an irreversible operation.
  - An AI judge read all 3 captured unit(s) of tool text and found none that tries to manipulate the model reading it.
- **Capabilities**: 100/100
  - Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.

**Unverified: 1 category.** A category scored 0 because we could not verify it: a data source with nothing on this package, evidence we could not reach, or a check we could not run. We only credit what we can confirm.

## Install

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

RogueGPT runs locally as a PyPI package, launched with uvx --from 'roguegpt[mcp]' roguegpt mcp. Ready-made configuration for Claude, Cursor, VS Code, Codex and 3 more is on this page, copied from each client's own documentation.

### Claude

```bash
claude mcp add aloth-roguegpt -- uvx --from 'roguegpt[mcp]' roguegpt mcp
```

### Cursor

```json
{
  "mcpServers": {
    "aloth-roguegpt": {
      "command": "uvx",
      "args": [
        "--from",
        "roguegpt[mcp]",
        "roguegpt",
        "mcp"
      ]
    }
  }
}
```

### VS Code

```json
{
  "servers": {
    "aloth-roguegpt": {
      "command": "uvx",
      "args": [
        "--from",
        "roguegpt[mcp]",
        "roguegpt",
        "mcp"
      ]
    }
  }
}
```

### Codex

```bash
codex mcp add aloth-roguegpt -- uvx --from 'roguegpt[mcp]' roguegpt mcp
```

### opencode

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

### Hermes

```yaml
mcp_servers:
  aloth-roguegpt:
    command: "uvx"
    args: ["--from", "roguegpt[mcp]", "roguegpt", "mcp"]
```

### Netclaw

```json
{
  "McpServers": {
    "aloth-roguegpt": {
      "Transport": "stdio",
      "Command": "uvx",
      "Arguments": [
        "--from",
        "roguegpt[mcp]",
        "roguegpt",
        "mcp"
      ]
    }
  }
}
```

### Other

```json
{
  "mcpServers": {
    "aloth-roguegpt": {
      "command": "uvx",
      "args": [
        "--from",
        "roguegpt[mcp]",
        "roguegpt",
        "mcp"
      ]
    }
  }
}
```

## 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.

### 2026-11-20 (score 64, −15)

- [security regression] Malware scan: pass → unverified

### 2026-11-19 (score 79, +15)

- [security improvement] Malware scan: unverified → pass

### 2026-11-15 (score 64, −15)

- [security regression] Malware scan: pass → unverified

### 2026-11-14 (score 79, +15)

- [security improvement] Malware scan: unverified → pass

### 2026-11-13 (score 64, −15)

- [security regression] Malware scan: pass → unverified

### 2026-11-12 (score 79, +15)

- [security improvement] Malware scan: unverified → pass

### 2026-11-11 (score 64, −15)

- [security regression] Malware scan: pass → unverified

### 2026-11-08 (score 79, +15)

- [security improvement] Malware scan: unverified → pass

## MCP tools (2)

### `ingest_fragment` (~262 tokens)

Ingest a news fragment into the RogueGPT dataset.

Args:
    content: The news text (required).
    origin: "Human" or "Machine" (required).
    is_fake: Whether the fragment is fake news (required).
    iso_language: ISO 639-1 language code (default: "en").
    machine_model: Model identifier for Machine origin (must match prompt_engine.json, e.g. "openai_gpt-4o_2024-08-06").
    machine_prompt: The prompt used to generate the fragment (recommended for Machine origin).
    human_outlet: Publishing outlet name for Human origin (required if Human).
    human_url: Source URL for Human origin (recommended).
    strict_model: If True, reject unknown model names. If False, warn but allow.

Returns:
    {"fragment_id": str, "warnings": list[str]} on success.

Input parameters:

- `content` (string, required)
- `human_outlet` (string)
- `human_url` (string)
- `is_fake` (boolean, required)
- `iso_language` (string)
- `machine_model` (string)
- `machine_prompt` (string)
- `origin` (string, required)
- `strict_model` (boolean)

### `retrieve_fragments` (~150 tokens)

Retrieve random fragments from the RogueGPT dataset.

Args:
    n: Number of fragments to return (default: 1, max: 50).
    origin: Filter by "Human" or "Machine" (optional).
    model: Filter by model identifier, e.g. "openai_gpt-4o_2024-08-06" (optional).
    language: Filter by ISO language code (optional).
    is_fake: Filter by fake news status (optional).

Returns:
    {"fragments": [...], "count": int}

Input parameters:

- `is_fake`
- `language`
- `model`
- `n` (integer)
- `origin`

## Diagnostics

Captured diagnostic sections: Provenance, Install scripts, Dependencies. The full working is on the page: https://verifymcp.io/servers/aloth-roguegpt/roguegpt#diagnostics

## Score history

- 2026-11-21: 64
- 2026-11-20: 64
- 2026-11-19: 79
- 2026-11-18: 64
- 2026-11-17: 64
- 2026-11-16: 64
- 2026-11-15: 64
- 2026-11-14: 79
- 2026-11-13: 64
- 2026-11-12: 79
- 2026-11-11: 64
- 2026-11-10: 79
- 2026-11-09: 79
- 2026-11-08: 79
- 2026-11-07: 64

## Common questions

### What is the RogueGPT MCP server?

RogueGPT is an MCP server listed in the public MCP registry as io.github.aloth/roguegpt. Store and retrieve controlled AI news stimuli with generation metadata for misinformation research. This page covers its PyPI package (roguegpt).

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

RogueGPT scores 64 out of 100 on VerifyMCP. We found no known CVEs affecting it as of 21 November 2026. 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 RogueGPT MCP server expose?

RogueGPT exposes 2 tools: ingest_fragment, retrieve_fragments. Their descriptions and schemas cost roughly 412 tokens of context every time the server is loaded.

### Is the RogueGPT MCP server still maintained?

RogueGPT is still listed as active in the MCP registry. We last reached this channel on 21 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 RogueGPT MCP server under?

RogueGPT declares the GPL-3.0-or-later licence, which is OSI-approved. That covers the source only, and says nothing about the cost of any service it calls.

### What did VerifyMCP test on the RogueGPT MCP server?

VerifyMCP ran 14 checks on RogueGPT, covering Known CVEs, Install scripts, Dependency health, Source repository and 10 more. 2 items could not be completed, a gap on our side rather than a finding about RogueGPT: Malware scan and Stability. One category scores 0 for that reason, because we only credit what we can confirm. Endpoint Security and Transport & Reachability do not apply to a PyPI package, so they were not tested. The score does not measure everything, and the scoring documentation lists what it leaves out.

## Links

- PyPI project: https://pypi.org/project/roguegpt/
- Socket report: https://socket.dev/pypi/package/roguegpt
- Repository: https://github.com/aloth/RogueGPT
- Website: https://aloth.github.io/RogueGPT/
- Changelog RSS feed: https://verifymcp.io/servers/aloth-roguegpt/roguegpt.xml
- Changelog JSON feed: https://verifymcp.io/servers/aloth-roguegpt/roguegpt/changelog.json
- Trust report (JSON): https://verifymcp.io/servers/aloth-roguegpt/roguegpt.json
- HTML version of this page: https://verifymcp.io/servers/aloth-roguegpt/roguegpt
