Is Webtools MCP Server safe for production use?
No. The README explicitly states the software is AI‑assisted, provided as‑is, and should NOT be used in production without thorough testing. It may contain errors or security vulnerabilities.
@misterboe
基本信息
暂无概览
使用下面的配置,将此服务器添加到你的 MCP 客户端。
{
"mcpServers": {
"webtools-mcp-server": {
"command": "npx",
"args": [
"@bschauer/webtools-mcp-server"
]
}
}
}Get the HTML content of a webpage. Automatically handles retries and proxy if needed.
Get the webpage content in Markdown format, including links and images. Handles blocked access automatically.
Take a screenshot of a webpage or specific element on the page with custom device emulation
Debug a webpage by capturing console output, network requests, errors, and layout thrashing with custom device emulation. Includes advanced response size management with pagination, output limits, and compact formatting to stay within MCP token limits.
Run a Lighthouse audit on a webpage to generate a comprehensive performance report with detailed resource analysis. The report includes specific file paths, resource sizes, and performance metrics similar to Chrome DevTools. Identifies exact files causing performance issues without offering improvement suggestions.
Perform a detailed performance analysis with specialized modules for layout thrashing, CSS variables impact, JavaScript execution timeline, long tasks breakdown, memory and DOM growth analysis, and resource loading optimization. Provides actionable recommendations for performance improvements.
Analyze JavaScript and CSS coverage to identify unused code and optimization opportunities. Uses Chrome DevTools Protocol Coverage API to provide detailed insights into code usage.
Analyze Core Web Vitals metrics (LCP, CLS, FID/INP, TTFB) and identify problematic elements affecting these metrics. Uses Performance Observer API to provide detailed insights into real user experience metrics.
Analyze network activity and resource loading performance. Provides detailed insights into network requests, timing, and optimization opportunities.
Run performance tests across different devices and network conditions. Compare results and identify device-specific or network-specific issues.
A Model Context Protocol server that provides comprehensive web analysis tools, including HTML extraction, markdown conversion, screenshot capture, a debug console, advanced performance analysis, and Lighthouse-powered web audits. It is designed for developers using Claude Desktop or Claude Code to analyze websites for content, performance, accessibility, and SEO.
Install globally with npm install -g @bschauer/webtools-mcp-server or run directly with npx @bschauer/webtools-mcp-server. Configure it in Claude Desktop by adding a JSON entry under mcpServers, or add it via claude mcp add in Claude Code. Token usage can be optimized by setting the ENABLED_TOOLS environment variable or using the --tools CLI argument with a preset (e.g., BASIC, WEB, PERFORMANCE) or a comma-separated list of individual tool names.
No. The README explicitly states the software is AI‑assisted, provided as‑is, and should NOT be used in production without thorough testing. It may contain errors or security vulnerabilities.
Node.js version 14 or higher is required. Chrome/Chromium is automatically provided by Puppeteer — no separate installation needed.
Set the `ENABLED_TOOLS` environment variable to a preset (e.g., `BASIC` for ~1k tokens) or use the `--tools` CLI argument with a preset or comma‑separated tool names. The `BASIC` preset reduces token usage by 89%.
Create a configuration file at `~/.mcp/webtools-mcp-server.config.json`. It supports proxy settings, browser viewport, device presets, and network condition profiles.
PickFu MCP is a Model Context Protocol (MCP) server that connects AI assistants, developers, marketers, product managers, and AI agents to PickFu's consumer research platform. It enables users to create surveys, conduct
This open-source curriculum introduces the fundamentals of Model Context Protocol (MCP) through real-world, cross-language examples in .NET, Java, TypeScript, JavaScript, Rust and Python. Designed for developers, it focuses on practical techniques for building modular, scalable,

B2B competitive intelligence, live sales battlecards, 5-axis ICP prospect fit scoring, and tech stack teardowns over MCP and REST with cited public-web evidence.

DeepMark helps teachers deliver rapid, consistent marking with meaningful feedback for every student — in a fraction of the time. What once took a week, now takes one free period.

Model Context Protocol Servers
评论