@shiplightai/mcp 0.1.17 → 0.1.18

package/README.md

@@ -1,6 +1,6 @@
 # @shiplightai/mcp
 
-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.
+UI automation MCP for agentic development workflows. Lets AI coding agents (Claude Code, Cursor, Windsurf, etc.) verify the UI changes they make — closing the build-verify loop automatically. Every interaction is captured as a human-readable step, producing rerunnable regression tests.
 
 ## Quick Start
 
@@ -20,9 +20,6 @@ Add to your MCP config (e.g., `.cursor/mcp.json`):
     "shiplight": {
       "command": "npx",
       "args": ["-y", "@shiplightai/mcp@latest"]
-    },
-    "env": {
-      "PWDEBUG": "console"
     }
   }
 }
@@ -60,10 +57,10 @@ Pass environment variables through your MCP config:
 
 Once connected, your AI coding agent can:
 
-- **Browse and interact** — Open pages, click elements, fill forms, navigate
-- **Verify UI** — Assert visual conditions using AI ("Verify the success message is displayed")
-- **Generate local tests** — Scaffold a Playwright project and write `.test.yaml` files with captured action entities for fast, deterministic replay
-- **Manage cloud test cases** — Create, run, and review test cases on Shiplight's cloud platform (requires `API_TOKEN`)
+- **Verify its own UI changes** — Open pages, interact with elements, and assert visual conditions using AI ("Verify the success message is displayed")
+- **Debug UI issues** — Inspect console errors and network failures directly from the browser session
+- **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
+- **Sync to the cloud** — Manage test cases on Shiplight's cloud platform for team-wide regression coverage (requires `API_TOKEN`)
 
 ## Links