A Model Context Protocol (MCP) server that provides comprehensive website snapshot capabilities using Playwright. This server enables LLMs to capture and analyze web pages through structured accessibility snapshots, network monitoring, and console message collection.

• 🚀 Fast and lightweight: Uses Playwright's accessibility tree for efficient snapshots
• 🎯 LLM-optimized: Structured data output designed specifically for AI consumption
• 📊 Comprehensive monitoring: Captures network requests, responses, and console messages
• 🔍 Element references: Adds unique identifiers to interactive elements for precise targeting
• 🛡️ Production-ready: Built-in error handling, resource limits, and timeout management
• ✅ Well-tested: Comprehensive test suite with code coverage

• Python 3.11 or newer
• VS Code, Cursor, Windsurf, Claude Desktop or any other MCP client

First, install the MCP Web Snapshot server with your client. A typical configuration looks like this:

{
  "mcpServers": {
    "mcp-web-snapshot": {
      "command": "uv",
      "args": [
        "--directory",
        "/path/to/mcp-web-snapshot",
        "run",
        "python",
        "src/server.py"
      ]
    }
  }
}

You can install the MCP Web Snapshot server using the VS Code CLI:

# For VS Code
code --add-mcp '{"name":"mcp-web-snapshot","command":"uv","args":["--directory","/path/to/mcp-web-snapshot","run","python","src/server.py"]}'

After installation, the MCP Web Snapshot server will be available for use with your GitHub Copilot agent in VS Code.

Go to Cursor Settings → MCP → Add new MCP Server. Name to your liking, use command type with the command uv and args ["--directory", "/path/to/mcp-web-snapshot", "run", "python", "src/server.py"].

{
  "mcpServers": {
    "mcp-web-snapshot": {
      "command": "uv",
      "args": [
        "--directory",
        "/path/to/mcp-web-snapshot",
        "run",
        "python",
        "src/server.py"
      ]
    }
  }
}

1. Clone this repository:

git clone https://github.com/your-username/mcp-web-snapshot.git
cd mcp-web-snapshot

2. Install dependencies using uv:

uv sync

3. Install Playwright browsers:

uv run playwright install

4. Run the server:

uv run python src/server.py

├── src/
│   ├── server.py               # Main MCP server entry point
│   ├── registry.py             # Tool registration logic
│   └── tools/
│       ├── __init__.py
│       └── snapshot_url.py     # Web snapshot implementation
├── tests/                      # Test suite
│   ├── __init__.py
│   ├── test_snapshot_url.py    # Unit tests for website_snapshot
│   └── README.md               # Test documentation
├── pyproject.toml              # Project configuration
├── pytest.ini                  # Pytest configuration
├── uv.lock                     # Lock file for dependencies
└── README.md                   # This file

The project includes a comprehensive test suite using pytest:

# Run all tests
uv run pytest

# Run with verbose output
uv run pytest -v

# Run with coverage report
PYTHONPATH=. uv run pytest --cov=src.tools.snapshot_url --cov-report=term-missing

Test coverage currently stands at 92%, covering:

• Successful snapshot capture and formatting
• Network request and console message monitoring
• URL validation
• Error handling and recovery

Tool: website_snapshot

Description: Take comprehensive snapshots of web pages with monitoring capabilities

Parameters:

• target_url (string): The URL to capture (must be a valid URL with protocol)

Features:

• 🎭 Accessibility Snapshot: Captures the complete accessibility tree structure
• 🌐 Network Monitoring: Records all network requests and responses during page load
• 🖥️ Console Messages: Captures client-side console output (logs, warnings, errors)
• 🎯 Element References: Adds unique reference IDs to interactive elements
• 📊 Performance Metrics: Provides summary of captured elements and network activity

Example Usage:

# Through MCP client
result = await website_snapshot("https://example.com")

Output Structure:

✅ Captured snapshot with 25 elements, 12 requests, 0 console messages
🔍 Example Website - Home Page
📍 https://example.com

🎭 Accessibility Snapshot:
- navigation "Main":
  - link "Home": [ref=1]
  - link "About": [ref=2]
  - button "Contact" [ref=3]
- main:
  - heading "Welcome to Example"
  - link "Get Started": [ref=4]

🌐 Network Requests:
🌐 GET https://example.com
   Status: 200
   Response: <!DOCTYPE html><html>...

🖥️ Console:
No console messages

🎯 Element References:
[ref=1]: link "Home"
[ref=2]: link "About"
[ref=3]: button "Contact"
[ref=4]: link "Get Started"

The server can be configured through the CONFIG dictionary in src/tools/snapshot_url.py:

CONFIG = {
    "viewport": {"width": 1920, "height": 1080},
    "user_agent": "Mozilla/5.0 (X11; Linux x86_64) AppleWebKit/537.36",
    "timeout": 15000,  # 15 seconds
}

• Viewport Size: Adjust browser window dimensions
• User Agent: Customize browser identification
• Timeout: Control maximum wait time for page operations
• Content Filtering: Modify response body size limits and content type filters

Capture comprehensive page state for automated test generation:

"Please take a snapshot of https://myapp.com/login and help me create Page Object Model classes based on the discovered elements and structure."

Extract structured data for content analysis and monitoring:

"Take a snapshot of https://competitor.com/pricing and analyze any pricing changes or new features compared to what we discussed last week."

Leverage accessibility tree data for compliance checking:

"Please capture a snapshot of https://myapp.com and identify any accessibility issues or areas for improvement based on WCAG guidelines."

Monitor network activity to understand application behavior:

"Take a snapshot of https://dashboard.example.com after I log in and show me what API calls are being made so I can understand the data flow."

Generate test scenarios based on captured interactions:

"Snapshot https://myapp.com/checkout and help me create comprehensive test cases that cover all the interactive elements and user workflows."

The server includes comprehensive error handling:

• Invalid URLs: Returns helpful error messages for malformed URLs
• Network Timeouts: Configurable timeout limits with graceful fallbacks
• Browser Crashes: Automatic cleanup and resource management
• Content Limits: Smart filtering of large response bodies to prevent memory issues

1. Fork the repository
2. Create a feature branch: git checkout -b feature-name
3. Make your changes and add tests
4. Run tests: uv run pytest
5. Check test coverage: PYTHONPATH=. uv run pytest --cov=src.tools.snapshot_url --cov-report=term-missing
6. Ensure code style compliance: uv run ruff check
7. Submit a pull request

Please ensure all tests pass and maintain or improve the current test coverage.

This project is licensed under the MIT License - see the LICENSE file for details.

• Inspired by MCP Server Website Snapshot article
• Built on the foundation of Microsoft's Playwright MCP
• Powered by Playwright for reliable browser automation
• Uses Model Context Protocol for LLM integration

• Playwright MCP - Interactive browser automation MCP server
• MCP Python SDK - MCP server python framework