MCP 服务器目录
共收录 462 个 MCP(Model Context Protocol)服务器,给 AI Agent 接上浏览器、数据库、搜索等工具能力。
webrecipe
浏览器自动化Save how to read a public web page once, then fetch fresh items as JSON without a browser.
browserbash
浏览器自动化Plain-English browser tests for AI agents: real Chrome, deterministic verdicts. Free, no API keys.
Oya Browser
浏览器自动化Real Chrome for agents: start a browser, read pages as numbered markdown, click, type, hand off.
novada-mcp
浏览器自动化Search, extract, crawl, map, research, scrape 16 platforms, browser automation, proxy — one API key.
bun-uia
浏览器自动化Playwright for the Windows desktop, from Bun — drive native GUIs via UI Automation + MCP.
Spicrawl
浏览器自动化Web scraping to Markdown and structured data, screenshots, batch jobs and browser sessions.
ScrapeAtlas
浏览器自动化Unified social scraper MCP — profiles, posts, videos across ~40 platforms via Streamable HTTP.
Depop Scraper & Monitor: New Listings, Price & Sold Alerts
浏览器自动化Depop listings for searches or URLs, with alerts on new listings, price drops and sales.
Ghost
浏览器自动化Verified desktop control for agents on Windows and Linux: apps with no API, windows, shell, browser.
chromeflow
浏览器自动化Lets Claude Code or Codex CLI drive your real Chrome — sessions intact, 28 browser tools.
acrawl
浏览器自动化Autonomous web crawler. 17 browser tools + goal-driven run_goal agent. Single binary, stealth.
toolpiper
浏览器自动化On-device MCP tools for macOS: local AI, speech, vision, browser automation, system control.
html-to-markdown-mcp
浏览器自动化Convert HTML to Markdown or strip to plain text. For web-scraping agents.
WaveXisMCP
浏览器自动化220 browser automation tools for Chrome, Edge, and Firefox via CDP + BiDi. 100% Python.
kite-lite
浏览器自动化Fetch, parse, screenshot and browse pages via MCP without a real browser -- no JS execution.
chrome-mcp
浏览器自动化Drive your real Chrome over MCP: real logins and cookies, multi-tab automation, deny-all by default.
Obscura MCP
浏览器自动化MCP server adapter for Obscura Rust headless browser — web scraping with anti-detection.
Data Enrichment & Web Scraper API
浏览器自动化Enrich IPs, emails, domains, companies. Scrape SEC, news, jobs, Crunchbase. Bitcoin pay-per-use.
CSS SOTA
浏览器自动化What CSS you can actually ship today, from live Baseline data and MDN browser-compat-data.
Tap
浏览器自动化Browser MCP for logged-in tasks. Uses your Chrome — credentials stay local. Zero-token replay.
Licium
浏览器自动化Clean rows from public pages that break ordinary scrapers, plus a bounty board where agents earn.
BrowserTap MCP
浏览器自动化MCP server that drives the real Chrome you already use, through an extension and CDP.
KeyID
浏览器自动化Signup sessions, browser continuity, email, SMS, and OTP/TOTP infrastructure for AI agents.
KitchenSink4Web
浏览器自动化Browser MCP server: budgeted page reads, honest unread accounting, structured extraction.