# darkmoon

An MCP server for your own Darkmoon Pro instance: launch an authorized pentest run, then check its status, campaigns and findings from the agent.

- plugin · `type=plugin` · Claude Code, Codex · ★ 1596 repo stars
- Author: ASC-IT
- License: GPL-3.0-only · policy=link-only · description only; the file stays with the author
- Source: https://github.com/hashgraph-online/awesome-codex-plugins/tree/HEAD/plugins/ASCIT31/darkmoon-mcp-server
- Updated: 2026-10-29
- Security check: automated, 2026-11-16 (text and 3 script files) — no signs of malicious code found.
- HTML: https://affpapa.org/en/nevibecode/plugins/darkmoon

## What it does

The plugin runs an MCP server, `@darkmoon_ai/mcp-server`, that connects your coding agent to a Darkmoon Pro dashboard. Four tools come with it. `run_pentest` kicks off an assessment of one target you are allowed to test and hands back a `run_id`; `get_run_status` reports where that run stands; `list_campaigns` and `get_findings` only read, listing campaigns and returning vulnerabilities with severity counts.

The server starts with `npx -y @darkmoon_ai/mcp-server`. The dashboard has to be your own: Darkmoon's engine and CLI are open source, but this server talks to the Pro Dashboard API, which ships self-hosted and has no public endpoint — so `DARKMOON_BASE_URL` points at your instance. Authentication takes either `DARKMOON_USERNAME` plus `DARKMOON_PASSWORD` or a pre-issued `DARKMOON_TOKEN`; each call requests a fresh JWT instead of reusing a cached one. `DARKMOON_TIMEOUT_MS` overrides the 60000 ms request timeout.

\`run_pentest` changes state, so aim it at systems you own or have written permission to test. Findings can be wrong, and a person has to review them.

## Install

### Claude Code (native platform)

**Plugin marketplace**
In the agent chat (not a shell):
```text
/plugin marketplace add hashgraph-online/awesome-codex-plugins
```
In the agent chat (not a shell):
```text
/plugin install darkmoon@awesome-codex-plugins
```

## When to use it
- start a scan of a test environment and get the `run_id`
- find out whether a run finished or errored out
- browse dashboard campaigns without leaving the chat
- pull a campaign's vulnerabilities grouped by severity
- review findings before opening the dashboard yourself

## Example prompts
- Start a pentest on `staging.example.com` with `run_pentest` and give me the `run_id`.
- Check whether the last run finished cleanly or hit an error.
- List the campaigns and show findings for the newest one.

## Similar
- [autopilot](https://affpapa.org/en/nevibecode/commands/autopilot.md) — command · ★ 16193 repo stars
- [SkillAudit](https://affpapa.org/en/nevibecode/mcp/skillaudit.md) — MCP server · 4310 installs
- [inter-agent-comm-security-detection](https://affpapa.org/en/nevibecode/skills/inter-agent-comm-security-detection.md) — skill · ★ 7607 repo stars
- [security-testing](https://affpapa.org/en/nevibecode/skills/aj-geddes-security-testing.md) — skill · 610 installs
- [Security Auditor](https://affpapa.org/en/nevibecode/mcp/security-auditor.md) — MCP server · 148 installs
- [triage-finding](https://affpapa.org/en/nevibecode/skills/triage-finding.md) — skill · 30 installs

From the same set: [hashgraph-online/awesome-codex-plugins](https://affpapa.org/en/nevibecode/by/hashgraph-online/awesome-codex-plugins.md) — 391 cards

---
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
