> ## Documentation Index
> Fetch the complete documentation index at: https://sunpeak.ai/docs/llms.txt
> Use this file to discover all available pages before exploring further.

# sunpeak test

> Run E2E tests, visual regression, live host tests, and multi-model evals.

## Overview

The `sunpeak test` command runs automated tests for your MCP server. It supports E2E tests against the inspector, visual regression, live tests against real hosts, and multi-model evals.

```bash theme={null}
sunpeak test
```

With no flags, `sunpeak test` runs unit tests (Vitest, if configured) and E2E tests (Playwright). For standalone testing framework projects, only E2E tests run because unit tests aren't scaffolded. For sunpeak app framework projects, both unit and E2E tests run by default.

Live tests and evals are never included in the default run because they require API keys and cost money.

## Options

| Flag                | Description                                                     |
| ------------------- | --------------------------------------------------------------- |
| `--e2e`             | Run E2E tests only (Playwright + inspector)                     |
| `--visual`          | Run E2E tests with visual regression comparison                 |
| `--visual --update` | Update visual regression baselines                              |
| `--live`            | Run live tests against real hosts (ChatGPT)                     |
| `--eval`            | Run evals against multiple LLM models                           |
| `--unit`            | Run unit tests (sunpeak app framework only, Vitest + happy-dom) |

Flags are additive: `--e2e --live --eval` runs all three. `--visual` implies `--e2e`. `--update` implies `--visual`.

Extra arguments are passed through to the underlying test runner (Playwright or Vitest):

```bash theme={null}
sunpeak test --e2e --ui                    # Playwright UI mode
sunpeak test --e2e tests/e2e/albums.spec.ts  # Single file
sunpeak test --eval albums                 # Filter evals by name
```

## Subcommands

### `sunpeak test init`

Scaffold test infrastructure for an existing MCP server (not built with sunpeak):

```bash theme={null}
sunpeak test init
```

This generates:

* `tests/e2e/` with example Playwright specs and config
* `tests/simulations/` with example simulation JSON fixtures
* `tests/evals/` with eval config, `.env.example`, and example eval specs
* `tests/live/` with live test config and example specs

For sunpeak framework projects, `sunpeak new` scaffolds all of this automatically.

## Examples

```bash theme={null}
# Default: unit (if configured) + e2e
sunpeak test

# E2E tests only
sunpeak test --e2e

# Visual regression (compare against baselines)
sunpeak test --visual

# Update visual baselines
sunpeak test --visual --update

# Live tests against real ChatGPT
sunpeak test --live

# Evals against multiple LLM models
sunpeak test --eval

# Run everything
sunpeak test --e2e --live --eval
```

## See Also

<CardGroup cols={2}>
  <Card horizontal title="E2E Testing" icon="flask" href="/testing/e2e">
    Write Playwright tests against simulated hosts.
  </Card>

  <Card horizontal title="Visual Regression" icon="image" href="/testing/visual">
    Screenshot comparison and baseline management.
  </Card>

  <Card horizontal title="Live Testing" icon="globe" href="/testing/live">
    Test against real ChatGPT.
  </Card>

  <Card horizontal title="Evals" icon="chart-bar" href="/testing/evals">
    Multi-model tool calling tests.
  </Card>
</CardGroup>