Name: RogueGPT
Author: aloth

RogueGPT MCP

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

Grade A Local · stdio API key 2 tools v1.5.0 GPL-3.0

No reviews yet by alothPyPI Runs on your machine, nothing hosted

100/100

trust score

tools declared

local

runs on your machine

—

downloads a day

What it does

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

Quickstart

# 1 — add it to Claude Code
claude mcp add --scope user --env 'ROGUEGPT_MONGO_URI=${ROGUEGPT_MONGO_URI}' --transport stdio roguegpt-mcp '--' uvx --from 'roguegpt[mcp]' roguegpt-mcp

# 2 — ask your agent for something these tools do
#   ingest_fragment, retrieve_fragments

It needs ROGUEGPT_MONGO_URI: this reads it from your environment, so export it first.

RogueGPT costs nothing on mcprush: there is no plan to choose here, no cap to set and nothing mcprush can bill you for.

Publishernot claimed

aloth3 servers

3 categories

All 3 servers

Collected from a public index. Nobody has claimed this account, so nothing here was written by its author — claim it if it is yours.

Installation

Where are you running it?

Every route below installs the same thing and ends at the same approval screen. This one runs on your machine: your client starts RogueGPT as a process under your own user, with your files and your network, so the tool surface below is what it can do to your computer rather than to a server somewhere else. Its scan result is on the Security tab — read the surface before you approve it.

Claude Codedeclared by this listing

This is a public server: you run it yourself and this marketplace is not in the path. You need uv (docs.astral.sh/uv): uvx comes with it. Claude Code registers it in one command; --scope user makes it available in every project. Claude Code reads ROGUEGPT_MONGO_URI (MongoDB connection string for the fragment store) from your environment each time it starts the server, so the value stays out of its config: export it in your shell profile (macOS, Linux), or run setx ROGUEGPT_MONGO_URI … and open a new terminal (Windows). The '--' is in quotes so that PowerShell passes it on.

claude mcp add --scope user --env 'ROGUEGPT_MONGO_URI=${ROGUEGPT_MONGO_URI}' --transport stdio roguegpt-mcp '--' uvx --from 'roguegpt[mcp]' roguegpt-mcp

Reconnect, or start a new session, and the tools appear in the model’s tool list.

Free on mcprush, and it runs from its publisher’s own package: this marketplace is not in the path, so there is no key of ours to hold and no card to add.

What it asks of you

It reaches a system of yours, so it needs settings only you can give it: ROGUEGPT_MONGO_URI — MongoDB connection string for the fragment store. You set it in your own client’s config, on your machine — this marketplace never holds it.

What it writes

One config entry your client uses to start the process locally. A local server runs with your file system and your network, which is why it is priced without metering.

What you approve

2 tools, with what each one reads, writes and reaches shown before you agree — the same list on every route above. Read the tool surface.

Tool surface

What the model actually sees. Descriptions are diffed on every release — see version history.

Only tools that write or reach the network

Read from its source code. A server that builds its tool list when it starts can list more tools than this.

Ingest a news fragment into the RogueGPT dataset.

Parameter	Type	Required	Notes
content	string	yes	The news text (required).
origin	string	yes	"Human" or "Machine" (required).
is_fake	boolean	yes	Whether the fragment is fake news (required).
iso_language	string	no	ISO 639-1 language code (default: "en").
machine_model	string	no	Model identifier for Machine origin (must match prompt_engine.json, e.g. "openai_gpt-4o_2024-08-06").
machine_prompt	string	no	The prompt used to generate the fragment (recommended for Machine origin).
human_outlet	string	no	Publishing outlet name for Human origin (required if Human).
human_url	string	no	Source URL for Human origin (recommended).
strict_model	boolean	no	If True, reject unknown model names. If False, warn but allow.

Retrieve random fragments from the RogueGPT dataset.

Parameter	Type	Required	Notes
n	integer	no	Number of fragments to return (default: 1, max: 50).
origin	string	no	Filter by "Human" or "Machine" (optional).
model	string	no	Filter by model identifier, e.g. "openai_gpt-4o_2024-08-06" (optional).
language	string	no	Filter by ISO language code (optional).
is_fake	boolean	no	Filter by fake news status (optional).

Free

$0 forever

Every tool, no call limit
No card, and mcprush charges nothing for it
Source published under GPL-3.0
Runs on your machine — nothing of it reaches our gateway
Nothing to cap, because mcprush bills nothing

Nothing here is billable: mcprush charges nothing to install RogueGPT or to call it, at any volume.

ATrust score 100 / 100

Release 1.5.0 · scanned 8 Nov 2026

Two independent axes, because powerful and malicious are different questions. The grade is threat only. The capability level is blast radius, and it is never a penalty on the grade — it is priced as one subtract-only term in the score, where you can see it.

Threat score100

Client score100

Findings1 threat · 0 capability

Capabilityminimal

Coveragesource

Verificationsource

Surface digestac1064bb62f5a6a24e367f49c3654f0f722d682ff442e37821ff18cac5afaae1

Score vectorthreat 100 → client 100

Term	Level	What it prices	Points
capability-exposure	minimal	capability blast radius (minimal) — client exposure if the model is manipulated	−0
verification-discount	source	publisher verification (provenance) — cryptographic build provenance ties the artifact to its source	−0
coverage-honesty	source	inspection depth (source) — how much of the target the scan could see	−0

score = clamp(round(threatScore − E_cap − E_ver − E_cov), 0, 100). No model, no opinion, no network call at scoring time: the same methodology version against the same bytes always produces this number, and every line above is a field of the report rather than a summary of it.

What the scan could actually read

A grade is only as meaningful as its coverage, so the scanner publishes its own depth before it publishes its result.

Tool surfaceread

Implementation sourceread

Package metadataread

Live transportnot available

Tools were statically extracted from the published source (2 recovered), not enumerated from a running server. Tool-poisoning, Unicode-smuggling, capability and toxic-flow analysis ran on this inferred surface, but a mis-parsed registration could be missed or mis-attributed, so tool-derived findings are capped below “confirmed”. To grade the real runtime surface, scan the running server: --command "npx -y <package>".

Capability — what it could do if the model were manipulated

Tags derived from each tool’s schema and the implementation, not from what the tool calls itself. minimal is the level these add up to.

Tool	Capability tags	Why the tag was assigned
ingest_fragment	no tags
retrieve_fragments	no tags

Toxic-flow graph

The lethal trifecta, checked as a graph rather than as a checklist: untrusted input, a sensitive source and an external sink have to meet before there is a path worth worrying about.

The public result for this release does not print the flow graph, so there is nothing to show here. That is not the same as "no paths were found": what the scan did read is above, under coverage.

Supply chain and provenance

Integrityfirst-seen

Surface digestac1064bb62f5a6a2

Scanned2026-11-08

This is the first scan of this surface here, so there is nothing yet to compare it against.

Every result on this tab comes from one deterministic pass over the published package — offline, rule by rule, and auditable line by line above. Same methodology version, same bytes, same score.