LocatorLabs MCP Server
Generates intelligent Playwright locators with reliability rankings, creates Page Object Models, and runs test automation scripts directly from your IDE or AI assistant.
README
LocatorLabs MCP Server
šÆ Intelligent Playwright locator generation powered by AI
An MCP (Model Context Protocol) server that provides smart locator generation for Playwright test automation.
Works directly in VS Code (with GitHub Copilot), Cursor, Windsurf, Cline, and Claude Desktop. No extra apps needed - just your favorite IDE!
ā” Quick Install
VS Code (v1.99+) - Copy & run in terminal:
code --add-mcp '{"name":"locatorlabs","command":"npx","args":["-y","locatorlabs-mcp"]}'
Cursor:
cursor --add-mcp '{"name":"locatorlabs","command":"npx","args":["-y","locatorlabs-mcp"]}'
Windows PowerShell:
code --add-mcp '{\"name\":\"locatorlabs\",\"command\":\"npx\",\"args\":[\"-y\",\"locatorlabs-mcp\"]}'
⨠Features
| Feature | Description |
|---|---|
| šÆ Get Locators | Get all possible locators for any element (Playwright + Selenium formats) |
| š Analyze Page | Scan pages and identify all interactive elements |
| šļø Generate POM | Auto-generate Page Object classes for Playwright & Selenium |
| ā Run Tests | Execute Playwright tests and get pass/fail results |
| š Generate Tests | Create executable test scripts |
š§ Supported Frameworks
| Framework | Locators | Page Object Model |
|---|---|---|
| Playwright | ā
getByRole, getByTestId, etc. |
ā TypeScript, JavaScript, Python |
| Selenium | ā
By.id, By.xpath, By.cssSelector |
ā Java, Python, C# |
š Quick Start
For VS Code (v1.99+ with GitHub Copilot)
One-Line Install (Mac/Linux):
code --add-mcp '{"name":"locatorlabs","command":"npx","args":["-y","locatorlabs-mcp"]}'
One-Line Install (Windows PowerShell):
code --add-mcp '{\"name\":\"locatorlabs\",\"command\":\"npx\",\"args\":[\"-y\",\"locatorlabs-mcp\"]}'
Or Manual Setup:
- Open Command Palette (
Cmd+Shift+P/Ctrl+Shift+P) - Type:
MCP: Add Server - Select:
Command (stdio) - Command:
npx - Args:
-y locatorlabs-mcp
Using with GitHub Copilot:
- Enable Agent Mode: Settings ā Search
chat.agent.enabledā Enable - Open Copilot Chat (
Ctrl+Cmd+I/Ctrl+Alt+I) - Switch to Agent mode (dropdown at top)
- Chat: "Get locators for login button on https://saucedemo.com"
For Claude Desktop
Step 1: Open config file
- Mac:
~/Library/Application Support/Claude/claude_desktop_config.json - Windows:
%APPDATA%\Claude\claude_desktop_config.json
Step 2: Add this configuration:
{
"mcpServers": {
"locatorlabs": {
"command": "npx",
"args": ["-y", "locatorlabs-mcp"]
}
}
}
Step 3: Restart Claude Desktop
For Cursor IDE
One-Line Install:
cursor --add-mcp '{"name":"locatorlabs","command":"npx","args":["-y","locatorlabs-mcp"]}'
Or Manual: Go to Cursor Settings ā MCP ā Add new MCP Server
- Name:
locatorlabs - Command:
npx -y locatorlabs-mcp
For VS Code + Cline Extension
Add to Cline MCP settings:
{
"mcpServers": {
"locatorlabs": {
"command": "npx",
"args": ["-y", "locatorlabs-mcp"]
}
}
}
š Usage Examples
Just chat naturally:
Get Locators for an Element
"Get me all locators for the login button on https://www.saucedemo.com"
Response:
| Type | Locator | Reliability |
|---|---|---|
| testId | getByTestId('login-button') |
98% |
| role | getByRole('button', { name: 'Login' }) |
95% |
| id | locator('#login-button') |
90% |
Analyze Entire Page
"Analyze all form elements on https://www.saucedemo.com"
Generate Page Object Model
Playwright:
"Generate a TypeScript Page Object for https://www.saucedemo.com and call it LoginPage"
Selenium:
"Generate a Java Selenium Page Object for https://www.saucedemo.com and call it LoginPage"
"Generate a C# Selenium Page Object for https://www.saucedemo.com called LoginPage"
"Generate a Python Selenium POM for https://www.saucedemo.com named LoginPage"
Run a Test
"Run a test that logs into saucedemo.com with standard_user and secret_sauce, then verify Products page appears"
Response:
ā
Test PASSED (3.2s)
- Navigate to login page ā
- Enter username ā
- Enter password ā
- Click login ā
- Verify Products visible ā
Generate Test Script
"Generate a Python test script for the saucedemo login flow"
š ļø Available Tools
| Tool | Description |
|---|---|
get_locators |
Get all possible locators (Playwright + Selenium formats) |
analyze_page |
List all interactive elements on a page |
generate_page_object |
Create POM class (Playwright: TS/JS/Python, Selenium: Java/Python/C#) |
run_test |
Execute tests in real browser, get pass/fail |
generate_test |
Generate executable test scripts |
š¦ Supported Languages for Page Objects
| Language | Framework | Example Output |
|---|---|---|
typescript |
Playwright | page.getByRole('button') |
javascript |
Playwright | page.getByRole('button') |
python |
Playwright | page.get_by_role('button') |
java-selenium |
Selenium | @FindBy(id = "btn") |
python-selenium |
Selenium | By.ID, "btn" |
csharp-selenium |
Selenium | [FindsBy(How = How.Id)] |
šÆ Supported Test Actions
| Action | Description |
|---|---|
navigate |
Go to URL |
click |
Click element |
fill |
Enter text |
clear |
Clear input field |
check / uncheck |
Toggle checkbox |
select |
Select dropdown option |
hover |
Mouse hover |
press |
Keyboard key press |
assert_visible |
Verify element visible |
assert_hidden |
Verify element hidden |
assert_text |
Verify text content |
assert_value |
Verify input value |
assert_url |
Verify page URL |
assert_title |
Verify page title |
wait |
Wait for time |
wait_for_element |
Wait for element |
screenshot |
Capture screenshot |
š Locator Priority
LocatorLabs ranks locators by reliability:
- data-testid (98%) - Best, explicitly for testing
- Role + Name (95%) - Playwright recommended
- Label (90%) - Accessible
- ID (90%) - Stable if meaningful
- Placeholder (85%) - Good for inputs
- Text (75%) - May change
- CSS (60%) - Can be brittle
- XPath (40%) - Avoid unless necessary
š LocatorLabs vs Playwright MCP
| Feature | Playwright MCP | LocatorLabs MCP |
|---|---|---|
| Get all locators for element | ā | ā |
| Locator reliability ranking | ā | ā |
| Selenium locator format | ā | ā |
| Generate Playwright POM | ā | ā |
| Generate Selenium POM (Java/C#/Python) | ā | ā |
| Run tests with pass/fail | ā | ā |
| Browser automation | ā | ā |
| Device emulation | ā | ā |
They work great together! Use Playwright MCP for navigation/scraping, LocatorLabs MCP for locators/POMs/tests.
š Requirements
- Node.js 18+
- Playwright browsers (auto-installed on first run)
š§ Troubleshooting
Playwright browsers not installed
npx playwright install chromium
Permission issues on Mac
chmod +x ~/.npm/_npx/*/node_modules/.bin/locatorlabs-mcp
View logs (Claude Desktop)
tail -f ~/Library/Logs/Claude/mcp*.log
Auto-approve tools in VS Code
Add to settings.json:
{
"chat.tools.autoApprove": true
}
š¤ Contributing
Contributions welcome! Please open an issue or PR on GitHub.
šŗ Author
Naveen AutomationLabs
- YouTube: @naveenautomationlabs (500K+ subscribers)
- Website: naveenautomationlabs.com
- LinkedIn: Naveen AutomationLabs
š License
MIT
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.