Website Snapshot

Captures complete website snapshots using Playwright's browser automation engine, extracting the full accessibility tree (DOM structure with ARIA labels, roles, and semantic information) alongside rendered visual state. The server launches headless browser instances, navigates to target URLs, waits for page stabilization, and serializes the accessibility tree into a structured format that LLMs can reason about without requiring visual rendering.

Intercepts and logs all HTTP/HTTPS network requests made during page load using Playwright's network interception API, collecting request/response metadata (URLs, headers, status codes, timing) into HAR (HTTP Archive) format. Enables analysis of API calls, resource loading patterns, and network performance without requiring manual request inspection or proxy configuration.

Collects all console output (console.log, console.error, console.warn, console.info) and JavaScript errors/exceptions that occur during page load and interaction. Messages are timestamped and categorized by severity level, enabling LLMs to detect runtime errors, warnings, and debug information that indicate page health or functionality issues.

Implements the Model Context Protocol (MCP) server specification, registering website snapshot capabilities as callable tools that Claude and other MCP-compatible LLMs can invoke directly. Uses MCP's JSON-RPC transport layer to expose snapshot, network monitoring, and console logging functions with standardized schema definitions, enabling seamless integration into LLM agent workflows without custom API wrappers.

Implements intelligent page load detection by waiting for network idle state (no pending network requests for a configurable duration) and optionally waiting for specific DOM elements to appear. Uses Playwright's built-in waitForLoadState() and waitForSelector() APIs to ensure pages are fully rendered before capturing snapshots, preventing incomplete or partial captures of dynamically-loaded content.

Allows configuration of browser viewport dimensions and device emulation profiles (mobile, tablet, desktop) before capturing snapshots. Uses Playwright's device emulation to set user agent, viewport size, and device pixel ratio, enabling capture of responsive layouts and mobile-specific content variations without requiring multiple browser instances.

Supports loading and saving browser cookies and session storage to enable authenticated access to websites. Allows pre-loading cookies from a file or configuration before navigation, and optionally persisting cookies after snapshot capture for reuse in subsequent requests. Enables automation of authenticated workflows without storing credentials directly.

Allows injection of custom HTTP headers and user agent strings before making requests to websites. Uses Playwright's context.setExtraHTTPHeaders() to add custom headers (e.g., Authorization, X-Custom-Header) and device emulation to override user agent, enabling testing of header-dependent behavior and bypassing basic user agent detection.

Enables execution of arbitrary JavaScript code in the page context and simulation of user interactions (clicks, typing, scrolling) before snapshot capture. Uses Playwright's page.evaluate() for script execution and page.click(), page.type(), page.scroll() for interactions, allowing LLMs to trigger dynamic content loading or state changes before capturing snapshots.

Supports configuration of HTTP/HTTPS proxies and SOCKS proxies for routing all browser traffic through a proxy server. Uses Playwright's proxy configuration in browser context to redirect requests, enabling access to geographically-restricted content, IP rotation, or traffic inspection without modifying individual requests.