taobao-mcp
Provides browser automation for Taobao, enabling product search by keyword and retrieval of product details (title, price, image URL) via item ID or product page URL, using a logged-in browser session.
This server does not currently have a deployable release on Glama. Follow the repository's setup instructions to install and configure it for your MCP client, including any required credentials and local dependencies.
my-browser-mcp
An MCP server exposing browser automation tools, including Taobao product search/detail lookup via Playwright.
Setup
npm install
npx playwright install chromiumTaobao currently requires a logged-in session for both search and product-detail pages — a fresh, unauthenticated browser gets redirected to login.taobao.com. Log in once, manually, and the session is reused:
npm run login:taobaoThis opens a visible Chromium window at Taobao's login page. Log in yourself (QR scan or credentials — the script never touches your credentials, it just waits for you). Press Enter in the terminal once you're logged in, and the session is saved to auth/taobao-state.json (override the path with the TAOBAO_STORAGE_STATE env var). Re-run this whenever the session expires.
Related MCP server: PlayMCP Browser Automation Server
Run
npm run devRuns the MCP server over stdio. Point your MCP client (e.g. Claude Code) at npx tsx src/index.ts in this directory.
By default the browser runs headed (headless: false) so you can see what it's doing; set HEADLESS=true to run headless once you trust it's working.
Tools
open-page,click,get-page-content,screenshot— generic browser control.taobao-search-products— search by keyword, returns a best-effort list of{itemId, title, price, link, imageUrl}.taobao-get-product-detail— fetch{title, price, imageUrl}for one item, given an item id oritem.taobao.comURL.
Limitations
Best-effort scraping, not an official API. Taobao has no public product-search API for general use; this drives a real browser and parses rendered HTML/DOM. Selectors and page structure change without notice and may break these tools at any time.
Login required. Taobao gates search and item pages behind an authenticated session (enforced both via full-page redirects and via background API calls silently redirecting to
login.taobao.com). Runnpm run login:taobaofirst.No CAPTCHA bypass. If Taobao serves a verification challenge (slider CAPTCHA, risk-control block), the tools detect it and return an explanatory
errorfield instead of attempting to solve it — you'll need to complete it yourself vianpm run login:taobao.ToS. Automated access to Taobao may violate its Terms of Service. Use at your own risk, keep request volume low, and don't use this for anything resembling scraping at scale.
This server cannot be deployed
Maintenance
Related MCP Connectors
Official Browserless MCP server: browser automation, scraping, screenshots and PDFs for AI agents.
Hosted Web Crawler MCP server for Claude, ChatGPT and Cursor, with each action switched per account.
MCP server to assist with JxBrowser development.
Related MCP Servers
- AlicenseBqualityNot gradedmaintenanceA MCP server that provides browser automation tools, allowing users to navigate websites, take screenshots, click elements, fill forms, and execute JavaScript through Playwright.82Apache 2.0
- AlicenseCqualityFmaintenanceA comprehensive MCP server that provides powerful web automation tools using Playwright, enabling web scraping, testing, and browser interaction through natural language commands.3815MIT
- -licenseBqualityNot gradedmaintenanceA lightweight MCP server for browser automation using Playwright with essential tools for navigation, form interaction, and web scraping. Provides 16 core browser automation tools with minimal setup and fast performance.16-
- AlicenseAqualityFmaintenanceStateful MCP server wrapping Playwright for browser automation. Provides tools to navigate, interact, and extract data from web pages via a persistent browser session.191,038 npmMIT