@shiplightai/mcp 0.1.13 → 0.1.15
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.
- package/README.md +68 -0
- package/dist/index.js +231 -231
- package/package.json +1 -1
package/README.md
ADDED
|
@@ -0,0 +1,68 @@
|
|
|
1
|
+
# @shiplightai/mcp
|
|
2
|
+
|
|
3
|
+
MCP server for AI-powered web application testing. Gives AI coding agents (Claude Code, Cursor, Windsurf, etc.) the ability to control a browser, verify UI flows, and generate rerunnable YAML test files.
|
|
4
|
+
|
|
5
|
+
## Quick Start
|
|
6
|
+
|
|
7
|
+
### Claude Code
|
|
8
|
+
|
|
9
|
+
```bash
|
|
10
|
+
claude mcp add shiplight -e PWDEBUG=console -- npx -y @shiplightai/mcp@latest
|
|
11
|
+
```
|
|
12
|
+
|
|
13
|
+
### Cursor / Windsurf / Other MCP Clients
|
|
14
|
+
|
|
15
|
+
Add to your MCP config (e.g., `.cursor/mcp.json`):
|
|
16
|
+
|
|
17
|
+
```json
|
|
18
|
+
{
|
|
19
|
+
"mcpServers": {
|
|
20
|
+
"shiplight": {
|
|
21
|
+
"command": "npx",
|
|
22
|
+
"args": ["-y", "@shiplightai/mcp@latest"]
|
|
23
|
+
}
|
|
24
|
+
}
|
|
25
|
+
}
|
|
26
|
+
```
|
|
27
|
+
|
|
28
|
+
### Environment Variables
|
|
29
|
+
|
|
30
|
+
| Variable | Required | Description |
|
|
31
|
+
|---|---|---|
|
|
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
|
+
| `ANTHROPIC_API_KEY` | One AI key required | Anthropic API key (for Claude models) |
|
|
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) |
|
|
36
|
+
|
|
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
|
+
|
|
39
|
+
Pass environment variables through your MCP config:
|
|
40
|
+
|
|
41
|
+
```json
|
|
42
|
+
{
|
|
43
|
+
"mcpServers": {
|
|
44
|
+
"shiplight": {
|
|
45
|
+
"command": "npx",
|
|
46
|
+
"args": ["-y", "@shiplightai/mcp@latest"],
|
|
47
|
+
"env": {
|
|
48
|
+
"PWDEBUG": "console",
|
|
49
|
+
"ANTHROPIC_API_KEY": "sk-ant-..."
|
|
50
|
+
}
|
|
51
|
+
}
|
|
52
|
+
}
|
|
53
|
+
}
|
|
54
|
+
```
|
|
55
|
+
|
|
56
|
+
## What It Does
|
|
57
|
+
|
|
58
|
+
Once connected, your AI coding agent can:
|
|
59
|
+
|
|
60
|
+
- **Browse and interact** — Open pages, click elements, fill forms, navigate
|
|
61
|
+
- **Verify UI** — Assert visual conditions using AI ("Verify the success message is displayed")
|
|
62
|
+
- **Generate local tests** — Scaffold a Playwright project and write `.test.yaml` files with captured action entities for fast, deterministic replay
|
|
63
|
+
- **Manage cloud test cases** — Create, run, and review test cases on Shiplight's cloud platform (requires `API_TOKEN`)
|
|
64
|
+
|
|
65
|
+
## Links
|
|
66
|
+
|
|
67
|
+
- [Shiplight](https://shiplight.ai)
|
|
68
|
+
- [shiplightai npm package](https://www.npmjs.com/package/shiplightai) — Playwright plugin for running `.test.yaml` files locally
|