@shiplightai/mcp 0.1.32 → 0.1.34

This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
Files changed (3) hide show
  1. package/README.md +5 -3
  2. package/dist/index.js +378 -378
  3. package/package.json +1 -1
package/README.md CHANGED
@@ -32,7 +32,7 @@ Add to your MCP config (e.g., `.cursor/mcp.json`):
32
32
  | `PWDEBUG` | Yes | Must be set to `console`. Enables Playwright semantic locator generation (e.g., `getByRole`, `getByTestId`) for action entities. Without this, only XPath locators are available. |
33
33
  | `ANTHROPIC_API_KEY` | One AI key required | Anthropic API key (for Claude models) |
34
34
  | `GOOGLE_API_KEY` | One AI key required | Google AI API key (for Gemini models) |
35
- | `API_TOKEN` | No | Shiplight cloud API token (enables cloud features) |
35
+ | `SHIPLIGHT_API_TOKEN` | No | Shiplight cloud API token (enables cloud features) |
36
36
 
37
37
  At least one AI API key is needed for the test execution agent. The model is auto-detected from the key (`ANTHROPIC_API_KEY` → `claude-haiku-4-5`, `GOOGLE_API_KEY` → `gemini-2.5-pro`).
38
38
 
@@ -53,11 +53,13 @@ Pass environment variables through your MCP config:
53
53
  }
54
54
  ```
55
55
 
56
+ The server also reads inherited host environment variables, so you can export `SHIPLIGHT_API_TOKEN` before launching your MCP client instead of duplicating it in the MCP config.
57
+
56
58
  ## CLI Options
57
59
 
58
60
  | Option | Description |
59
61
  |--------|-------------|
60
- | `--cloud` | Enable cloud features (test case management, test results). Requires `API_TOKEN` environment variable. |
62
+ | `--cloud` | Enable cloud features (test case management, test results). Requires `SHIPLIGHT_API_TOKEN`. |
61
63
 
62
64
  ## What It Does
63
65
 
@@ -66,7 +68,7 @@ Once connected, your AI coding agent can:
66
68
  - **Verify its own UI changes** — Open pages, interact with elements, and assert visual conditions using AI ("Verify the success message is displayed")
67
69
  - **Debug UI issues** — Inspect console errors and network failures directly from the browser session
68
70
  - **Generate regression tests** — Every action is captured as a human-readable step, so sessions can be exported as `.test.yaml` files for fast, deterministic replay
69
- - **Sync to the cloud** — Manage test cases on Shiplight's cloud platform for team-wide regression coverage (requires `--cloud` and `API_TOKEN`)
71
+ - **Sync to the cloud** — Manage test cases on Shiplight's cloud platform for team-wide regression coverage (requires `--cloud` and `SHIPLIGHT_API_TOKEN`)
70
72
  - **Attach to existing Chrome tabs** — Control your existing Chrome tabs via the Shiplight AI extension without recreating login state or complex setups
71
73
 
72
74
  ## Links