Analyze findings from a simulation report
Compare two simulation runs for regressions or improvements
Launch a simulation test for an application
Set up a new application for AI testing
Diagnose failed or problematic simulation runs
Test your AI applications from Claude using Arato Simulate.
Arato Simulate evaluates AI chat and voice applications by running automated simulations with realistic user personas. This plugin connects Claude to the Arato platform, giving you access to all 25 Arato tools directly from your editor or desktop app.
/plugin marketplace add AratoAi/claude-code-plugin
/plugin install arato-simulate@arato-plugins
This gives you the full experience: MCP tools, skills, and the @simulation-operator agent.
Add the Arato MCP server to your Claude Desktop config:
macOS: ~/Library/Application Support/Claude/claude_desktop_config.json
Windows: %APPDATA%\Claude\claude_desktop_config.json
{
"mcpServers": {
"arato-simulate": {
"url": "https://simulate.arato.ai/mcp"
}
}
}
Restart Claude Desktop after saving. All 25 MCP tools will be available. Skills and agents are Claude Code-only.
The plugin uses OAuth 2.1 with PKCE — the recommended authentication method. On first use, Claude Code opens a browser window for you to log in to Arato. No API keys or config files needed. Your session is refreshed automatically.
Alternatively, for headless or CI environments, you can pass a bearer token directly. Create an API key under Settings > API Keys in the Arato UI, then set it in your Claude Code MCP settings:
{
"mcpServers": {
"arato-simulate": {
"url": "https://simulate.arato.ai/mcp",
"headers": {
"Authorization": "Bearer sk_your_api_key_here"
}
}
}
}
| Skill | Description |
|---|---|
/launch-test | Launch a simulation run — pick test suite, configure parallelism, monitor progress |
/setup-app | Onboard a new app — create application, generate brief, generate personas, first run |
/analyze-findings | Analyze findings from a completed simulation — severity grouping, patterns, remediation |
/triage-failures | Diagnose failed or problematic runs — check status, screenshots, error patterns |
/compare-runs | Compare two runs — identify regressions, improvements, severity changes |
| Agent | Description |
|---|---|
@simulation-operator | Expert Arato operator — guides you through the full testing workflow proactively |
All tools are provided by the Arato MCP server. The plugin connects to the server automatically.
| Tool | Description |
|---|---|
list_applications | List all applications in a workspace |
get_application | Get details of a specific application |
create_application | Create a new application with a name and URL |
| Tool | Description |
|---|---|
get_brief | Get the brief for an application |
comment_on_brief | Add a comment to refine the brief |
regenerate_brief | Regenerate the brief from scratch |
| Tool | Description |
|---|---|
list_virtual_users | List virtual users for an application |
generate_virtual_users | Generate virtual user personas |
| Tool | Description |
|---|---|
list_test_suites | List available test suites |
get_test_suite_tests | Get individual tests within a suite |
list_skills | List available testing skills |
| Tool | Description |
|---|---|
launch_run | Launch a simulation run |
get_run_status | Check run status |
get_run_progress | Get live per-persona progress |
stop_run | Stop a running simulation |
list_runs | List runs with optional status filter |
| Tool | Description |
|---|---|
get_report | Get the full report for a completed run |
list_reports | List simulation reports |
list_findings | List findings from a run |
| Tool | Description |
|---|---|
list_run_assets | List artifacts (screenshots, transcripts, videos, summaries) |
| Tool | Description |
|---|---|
view_run_dashboard | Interactive dashboard with live status and progress |
view_findings | Interactive findings explorer with filtering |
view_report | Interactive report viewer with summary metrics |
| Tool | Description |
|---|---|
list_workspaces | List available workspaces |
Full documentation is available at simulate.arato.ai/docs/mcp-integration.
MIT
External network access
Connects to servers outside your machine
Uses power tools
Uses Bash, Write, or Edit tools
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 aratoai/claude-code-plugin --plugin arato-simulateUnity Development Toolkit - Expert agents for scripting/refactoring/optimization, script templates, and Agent Skills for Unity C# development
Complete creative writing suite with 10 specialized agents covering the full writing process: research gathering, character development, story architecture, world-building, dialogue coaching, editing/review, outlining, content strategy, believability auditing, and prose style/voice analysis. Includes genre-specific guides, templates, and quality checklists.
Comprehensive .NET development skills for modern C#, ASP.NET, MAUI, Blazor, Aspire, EF Core, Native AOT, testing, security, performance optimization, CI/CD, and cloud-native applications
Complete collection of battle-tested Claude Code configs from an Anthropic hackathon winner - agents, skills, hooks, and rules evolved over 10+ months of intensive daily use
20 SEO/GEO skills and 5 commands on one shared contract for keyword research, content creation, technical audits, schema markup, monitoring, quality gates, entity truth, and campaign memory.
Comprehensive SEO analysis plugin for Claude Code. 25 sub-skills (21 core + 1 orchestrator + 1 framework + 2 extension mirrors) and 18 sub-agents cover technical SEO, content quality, schema, sitemaps, Core Web Vitals, local SEO, backlinks, AI/GEO, ecommerce, hreflang, SXO, clustering, drift monitoring, and Google APIs. Includes optional MCP extensions, SPA-aware rendering, portability, and hardened SSRF/DNS-rebinding safe fetchers.