Build and manage Rogue Arena scenarios — brainstorm company context and infrastructure via YML blueprints, implement via MCP tools, freeform canvas editing, and deployment debugging
Interactive scenario design — brainstorm company context, infrastructure, characters, and optional exploit paths. Produces scenario_part1.yml + scenario_part2.yml + scenario_part3.yml + exploit.yml. Triggers: 'build a lab', 'new scenario', 'update my scenario', 'design a network', 'add exploit path'.
Investigate deployment failures — Ansible errors, PowerShell debugging, plugin misconfigurations. Triggers: 'my deployment failed', 'deployment error', 'debug deploy', 'ansible failed', 'PowerShell error'. Requires a deployment ID.
Manual canvas work with MCP tools — add machines, swap plugins, wire VLANs, run validation. No guided pipeline. Triggers: 'work on my canvas', 'help me with architect tools', 'freeform mode', 'validate my canvas', 'is this ready to deploy'.
Execute a scenario blueprint — expands scenario.yml + exploit.yml into implementation.yml, builds infrastructure via MCP tools. Triggers: 'implement my scenario', 'build from YML'. Dispatched by architect-brainstorm after user approves.
Connect Claude Code to your Rogue Arena workspace. This repo includes:
macOS / Linux:
curl -fsSL https://raw.githubusercontent.com/rogue-labs-cyber/rogue-arena-mcp/main/install.sh | sh
Windows (PowerShell):
irm https://raw.githubusercontent.com/rogue-labs-cyber/rogue-arena-mcp/main/install.ps1 | iex
The installer checks for Node.js 18+, git, and Claude Code — and offers to install any that are missing. It then clones the repo, builds the MCP server, installs the skills, and configures Claude Code automatically.
Then authenticate:
rogue-mcp login
A browser window opens for you to sign in with your Rogue Arena account. Your token is stored in your OS keychain and auto-refreshes for 31 days.
That's it. Restart Claude Code and the tools are available.
The rogue-mcp CLI connects Claude Code to the Rogue Arena hub at arena.roguelabs.io. It proxies tool calls with your authentication, so Claude can:
| Skill | What it does |
|---|---|
| rogue-build-scenario | Design lab scenarios -- brainstorm company context and infrastructure, implement via MCP tools, debug deployments |
| rogue-active-deployment | Operate on running deployments -- execute commands, browse files, manage snapshots, test payloads against detections |
| rogue-plugin-dev | Develop Ansible plugins -- brainstorm offline install approaches, write YAML, manage vaults |
| rogue-curriculum-builder | Build course content -- create chapters, sections, CTF nodes, insert media |
Skills activate automatically when you ask Claude to do something that matches their triggers (e.g., "build a lab", "test this payload", "create a chapter").
You: "Build me a lab with a small financial company, 2 domains, 5 machines"
Claude: [activates rogue-build-scenario, brainstorms with you, builds via MCP tools]
You: "Deploy it and upload my C2 implant to the Windows workstation"
Claude: [activates rogue-active-deployment, deploys, uploads file]
You: "Test the implant against detections"
Claude: [activates rogue-maldev, snapshots, executes, checks Elastic, reverts]
rogue-mcp login # Authenticate with Rogue Arena
rogue-mcp logout # Sign out and revoke token
rogue-mcp whoami # Check auth status
rogue-mcp serve # Start the MCP server (Claude Code does this automatically)
Upload and download tools can read/write files on your local machine. Claude Code prompts you before each file operation. The server blocks access to sensitive directories (~/.ssh, ~/.aws, ~/.gnupg, etc.) as a safety net.
| Variable | Default | Description |
|---|---|---|
ROGUE_HUB_URL | https://arena.roguelabs.io | Hub API URL |
ROGUE_VAULTS_URL | Same as hub URL | Vaults service URL |
ROGUE_CLIENT_ID | rogue-mcp | Keycloak client ID |
Re-run the install command to pull the latest version.
# 1. Sign out (revokes the token and clears the keychain entry)
rogue-mcp logout
# 2. Remove the MCP server from Claude Code
claude mcp remove --scope user rogue-arena
# 3. Uninstall the global CLI
npm uninstall -g rogue-arena-mcp
# 4. Remove the local clone and plugin cache
rm -rf ~/.rogue-arena-mcp ~/.claude/plugins/cache/rogue-arena
Optional: remove the four Rogue Arena plugin entries from
~/.claude/plugins/installed_plugins.json if you want Claude Code to stop
listing them in /plugin.
"Not logged in" -- Run rogue-mcp login.
"Session expired" -- Token expired after ~31 days of inactivity. Run rogue-mcp login again.
Tools not appearing -- Restart Claude Code. Run rogue-mcp whoami to verify auth.
"No canvas set" -- Tell Claude to set a canvas, or use rogue_set_canvas with your canvas version ID from the Rogue Arena URL.
MIT
Own this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimOwn this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimBased on adoption, maintenance, documentation, and repository signals. Not a security audit or endorsement.
npx claudepluginhub rogue-labs-cyber/rogue-arena-mcp --plugin rogue-build-scenarioOperate on a user's running Rogue Arena deployment — list VMs, execute commands, browse filesystems, manage snapshots, transfer files. Triggers: 'run this on the VM', 'list my machines', 'upload this file', 'take a snapshot', 'revert', 'what's on this box', 'test this payload', 'grab that log'.
Local-first Ansible plugin development — brainstorm projects, research offline install approaches, and iterate on Ansible YAML with human-driven builds
Build and edit Rogue Arena curriculum content. Triggers: 'create chapters', 'add sections', 'build curriculum', 'edit content', 'add CTF nodes', 'insert media', 'unlock keys', 'populate chapters', 'reorder blocks', 'bulk create'. Handles LINEAR and CTF layouts with 21 CURRICULUM tools.
A growing collection of Claude-compatible academic workflow bundles. Covers scientific figures, manuscript writing and polishing, reviewer assessment, citation retrieval, data availability, paper reading, literature search, response letters, paper-to-PPTX conversion, and evidence-grounded Chinese invention patent drafting. Rules are organized as reusable skill folders with explicit workflows and quality checks.
Comprehensive feature development workflow with specialized agents for codebase exploration, architecture design, and quality review
Core skills library for Claude Code: TDD, debugging, collaboration patterns, and proven techniques
Harness-native ECC operator layer - 67 agents, 271 skills, 92 legacy command shims, reusable hooks, rules, selective install profiles, and production-ready workflows for Claude Code, Codex, OpenCode, Cursor, and related agent harnesses
UI/UX design intelligence. 67 styles, 161 palettes, 57 font pairings, 25 charts, 15 stacks (React, Next.js, Vue, Svelte, Astro, SwiftUI, React Native, Flutter, Tailwind, shadcn/ui, Nuxt, Jetpack Compose). Actions: plan, build, create, design, implement, review, fix, improve, optimize, enhance, refactor, check UI/UX code. Projects: website, landing page, dashboard, admin panel, e-commerce, SaaS, portfolio, blog, mobile app. Elements: button, modal, navbar, sidebar, card, table, form, chart. Styles: glassmorphism, claymorphism, minimalism, brutalism, neumorphism, bento grid, dark mode, responsive, skeuomorphism, flat design. Topics: color palette, accessibility, animation, layout, typography, font pairing, spacing, hover, shadow, gradient.
Comprehensive skill pack with 66 specialized skills for full-stack developers: 12 language experts (Python, TypeScript, Go, Rust, C++, Swift, Kotlin, C#, PHP, Java, SQL, JavaScript), 10 backend frameworks, 6 frontend/mobile, plus infrastructure, DevOps, security, and testing. Features progressive disclosure architecture for 50% faster loading.