@shiplightai/mcp 0.1.14 → 0.1.17
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 +6 -11
- package/package.json +1 -1
package/README.md
CHANGED
|
@@ -7,7 +7,7 @@ MCP server for AI-powered web application testing. Gives AI coding agents (Claud
|
|
|
7
7
|
### Claude Code
|
|
8
8
|
|
|
9
9
|
```bash
|
|
10
|
-
claude mcp add shiplight -- npx -y @shiplightai/mcp@latest
|
|
10
|
+
claude mcp add shiplight -e PWDEBUG=console -- npx -y @shiplightai/mcp@latest
|
|
11
11
|
```
|
|
12
12
|
|
|
13
13
|
### Cursor / Windsurf / Other MCP Clients
|
|
@@ -20,6 +20,9 @@ Add to your MCP config (e.g., `.cursor/mcp.json`):
|
|
|
20
20
|
"shiplight": {
|
|
21
21
|
"command": "npx",
|
|
22
22
|
"args": ["-y", "@shiplightai/mcp@latest"]
|
|
23
|
+
},
|
|
24
|
+
"env": {
|
|
25
|
+
"PWDEBUG": "console"
|
|
23
26
|
}
|
|
24
27
|
}
|
|
25
28
|
}
|
|
@@ -29,6 +32,7 @@ Add to your MCP config (e.g., `.cursor/mcp.json`):
|
|
|
29
32
|
|
|
30
33
|
| Variable | Required | Description |
|
|
31
34
|
|---|---|---|
|
|
35
|
+
| `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. |
|
|
32
36
|
| `ANTHROPIC_API_KEY` | One AI key required | Anthropic API key (for Claude models) |
|
|
33
37
|
| `GOOGLE_API_KEY` | One AI key required | Google AI API key (for Gemini models) |
|
|
34
38
|
| `API_TOKEN` | No | Shiplight cloud API token (enables cloud features) |
|
|
@@ -44,6 +48,7 @@ Pass environment variables through your MCP config:
|
|
|
44
48
|
"command": "npx",
|
|
45
49
|
"args": ["-y", "@shiplightai/mcp@latest"],
|
|
46
50
|
"env": {
|
|
51
|
+
"PWDEBUG": "console",
|
|
47
52
|
"ANTHROPIC_API_KEY": "sk-ant-..."
|
|
48
53
|
}
|
|
49
54
|
}
|
|
@@ -60,16 +65,6 @@ Once connected, your AI coding agent can:
|
|
|
60
65
|
- **Generate local tests** — Scaffold a Playwright project and write `.test.yaml` files with captured action entities for fast, deterministic replay
|
|
61
66
|
- **Manage cloud test cases** — Create, run, and review test cases on Shiplight's cloud platform (requires `API_TOKEN`)
|
|
62
67
|
|
|
63
|
-
## Resources
|
|
64
|
-
|
|
65
|
-
The server exposes schema resources that agents read automatically:
|
|
66
|
-
|
|
67
|
-
| Resource | Description |
|
|
68
|
-
|---|---|
|
|
69
|
-
| `shiplight://schemas/action-entity` | Browser action parameters — read automatically when a session starts |
|
|
70
|
-
| `shiplight://schemas/testflow-yaml-v1.2.0` | YAML test file format — read when creating local tests |
|
|
71
|
-
| `shiplight://schemas/testflow-json-v1.2.0` | JSON test flow format for cloud API (cloud mode only) |
|
|
72
|
-
|
|
73
68
|
## Links
|
|
74
69
|
|
|
75
70
|
- [Shiplight](https://shiplight.ai)
|