"A tool for comparing prices on Taobao" matching MCP servers:

An MCP server that exposes browser automation tools and Taobao product search/detail lookup via Playwright. It requires a logged-in Taobao session and is best-effort scraping, not an official API.

为大模型提供淘宝购物能力，支持搜索商品、加入购物车和生成待支付订单，人工完成付款。

Enables an AI companion to browse Taobao, maintain its own wishlist state machine, request approval under enforced budget rules, and hand a human-checkout list to the user, while all carting and payment remain human-controlled. It also returns login QR codes as images when authentication expires.

Enables AI assistants to search Taobao products, read details, and view product images through a local relay, with limited browsing and no ordering or cart actions.

Enables an LLM to order Ele.me/Taobao flash-purchase delivery by automating the H5 site: choose a delivery address, search nearby shops, view menus, add items to a cart, and generate an order that stops at the confirmation or checkout page without ever paying. Login and final payment are performed manually by a human over noVNC, with a configurable order-amount ceiling and structured prompts when risk-control or sliders appear.

Enables AI assistants to automate Taobao shopping tasks such as searching products, viewing details, adding to cart, placing orders, and making payments via Playwright.

Provides a local MCP server for AI-powered web crawling on Windows, enabling agents to directly crawl and extract web content without requiring WSL.

Enables AI agents to control a Playwright-driven browser through natural-language instructions, including page interaction and live browser task execution.

Provides agents with tools to score a page's AI readiness, check which AI crawlers robots.txt blocks, and assess passage citability—all performed locally.

A Playwright-based browser automation tool for AI agents, enabling web search, navigation, scraping, and page interaction through the Model Context Protocol.

Gives Claude control of a real, headed Chromium browser via Playwright, enabling web navigation, clicking, typing, screenshots, and JavaScript evaluation.

A CDP-native MCP server that lets AI agents drive a real Chrome browser with deep network/console inspection, robust page interaction, and the ability to reverse-engineer a site's API flow into runnable code with dependency chaining and replay verification.

Enables ZCode to control a real Chrome browser, including tabs, navigation, page content, clicks, form filling, keyboard input, scrolling, screenshots, and JavaScript evaluation through a local MCP bridge.

Enables searching GitHub repositories, fetching readable web page text, and querying a local book database through MCP tool calls.

Enables solving CAPTCHA challenges via MCP with bounded attempts and result validation.

Provides web crawling and browser automation capabilities with support for multiple content formats (HTML, JSON, PDF, screenshots, Markdown), page content extraction, console message monitoring, and network request tracking.

A Model Context Protocol server that provides real-time web search capabilities to AI assistants through pluggable search providers, currently integrated with the Brave Search API.

A Model Context Protocol server that provides web search capabilities using Google Custom Search API and webpage content extraction functionality.

Enables AI agents to drive real Google Chrome with stealth and captcha handling, using Patchright to avoid bot detection.

Enables authorized Ruflo workflows to recover from CAPTCHA interruptions via a single bounded stdio MCP tool with structured validation and human handoff.