42 个#browser MCP 服务器和客户端

Browserbase MCP Server

browserbase

Allow LLMs to control a browser with Browserbase and Stagehand

browser-use-mcp-server

co-browser

Browse the web, directly from Cursor etc.

Vibetest Use

browser-use

Vibetest MCP - automated QA testing using Browser-Use agents

🧪 Official MCP Server for Debugg AI

debugg-ai

Zero-Config, Fully AI-Managed End-to-End Testing for all code gen platforms.

Agent Browser

co-browser

One connection for all your MCP servers.

Gologin MCP Server

gologinapp

MCP server for managing Gologin browser profiles, proxies, fingerprints and cloud browser sessions through AI conversations

mult-fetch-mcp-server

lmcc-dev

A versatile MCP-compliant web content fetching tool that supports multiple modes (browser/node), formats (HTML/JSON/Markdown/Text), and intelligent proxy detection, with bilingual interface (English/Chinese).

Bring your real authenticated browser session to AI coding agents. Local-first MCP server + Chrome MV3 extension. No cloud. No telemetry.

Cubenest

Two OSS products on one rrweb substrate: tracelane (self-contained HTML test-failure replays for WDIO/Playwright/Cypress) + peek (local-first browser-session forensics + repro for AI coding agents, over MCP). No SaaS, no telemetry, local-first.

Browser Inspector Mcp

betson-uni

MCP server that gives AI coding tools the same CSS visibility you have in DevTools — rendered class names, full cascade, what's winning and why.

OpenWand

SunnyLich

Local MCP server that gives trusted AI clients desktop context through Wisp.

E2LLM / SiFR

e2llm

E2LLM gives your AI eyes and hands in a real browser — structured perception (SiFR) plus action, working with the AI you already use.

GDD (Giggly-Dazzling-Duckling)

Cap-of-tea

AI-controlled browser farm: run N isolated Chromium instances with 36 MCP tools for multi-device testing, screenshots, device emulation, network control, and console diagnostics.

Plasmate Mcp Server

plasmate-labs

MCP server for Plasmate. Use with Claude Code, Claude Desktop, Cursor, and Windsurf. npm install plasmate-mcp.

UXMachine

UXMachine

UXMachine measures a web page in a real browser and returns verifiable observations, each with its evidence and its limits. It opens the address on desktop (1280×800) and mobile (390×844) and follows the site's own links

Dazzle - Agentic Streaming

dazzle-labs

Cloud streaming for AI agents — isolated browser environments that render and broadcast your content to Twitch, Kick, Restream, and custom RTMP.

Aluvia

aluvia-connect

Give your AI agent unblockable browser access. Aluvia routes traffic through premium mobile carrier IPs to bypass 403s, CAPTCHAs, and WAFs automatically.

CodingBaby-Browser-MCP is a Model Context Protocol (MCP) tool server designed to communicate with Chrome browser extensions via WebSocket for browser automation control. The server provides multiple functionalities including web navigation, click operations, text input, key simul

GBOX Android MCP

babelcloud

GBOX provides environments for AI Agents to operate computer and mobile devices.

Control Google Chrome browser tabs, windows, and navigation

Memory Consolidation across vendors, owners, and time. Lithtrix gives AI agents persistent memory, credibility-scored web search, browser fetch, and a shared Commons pool — all under a stable ltx_ key that survives tool switches, session resets, and orchestrator changes. Self-reg

A concurrent browser MCP server that supports multiple parallel browser instances.

Fast browser automation MCP server. In-process Playwright, 58 tools (profiles: 9/28/58), cookie import from Chrome/Arc/Brave, handoff/resume for CAPTCHAs, iframe support, snapshot diffing. 41% faster than @playwright/mcp.

MCP server + Chrome extension that gives AI coding agents control of your real browser with existing sessions and logins. Works with Cursor, Claude, Windsurf, and any MCP client.

MCP server that annotates any web page with hover labels for AI assistants. Reverse proxy injection — zero browser extensions, works in any browser. 5 tools: annotate, get_elements, highlight_element, rescan_elements, inspect_mode.

screenshotrun-mcp

screenshotrun

Give your AI agent the ability to see any webpage. Capture screenshots from Claude, Cursor, or any MCP client. Supports full-page, dark mode, mobile emulation, OG image generation, base64 output, custom viewport, ad bloc

YetiBrowser MCP is a fully open-source implementation of the Browser MCP workflow. It links a Node-based MCP server with Chrome/Firefox extensions so Model Context Protocol clients—Codex/Claude Code, Cursor, Windsurf, MCP Inspector, or your own tools—can automate a real browser t

Documentation and assembly review for @nhtio/adk.

Wick

wickproject

Browser-grade web access for AI agents. Fetches any webpage using Chrome's actual network stack — identical TLS fingerprint to a real browser. Bypasses Cloudflare, Akamai, and other anti-bot systems that block standard HTTP clients. Returns clean markdown. Built by the creator of

One call turns any web page into a structured map — what it is, what's on it, and the actions an agent can take (search, add-to-cart, log in, paginate) — instead of raw HTML or screenshots. Served from a shared, always-current registry, so popular pages return in milliseconds.

Puppeteer MCP

iatsiuk

MCP server for browser automation via Puppeteer. Executes arbitrary JavaScript with direct access to Puppeteer Browser instance. Single "execute" tool runs your code in a sandboxed Node.js VM with a browser global - full Puppeteer API access in one call.

ThinkBrowse

dundas

Connect Claude Code, Cursor, and any MCP client to your real Chrome browser. Real sessions, real cookies, no headless conflicts. Works alongside your browser — no profile fights, no fresh sessions.

Official MCP server for the Site-Shot website screenshot API. Tools: capture_screenshot, capture_full_page. Real Chromium rendering, full-page capture up to 20,000 px, country proxies, and automatic ad & cookie-banner removal enabled by default — cleaner images, fewer vision toke

A Playwright-based MCP server that exposes a live browser as a traceable, inspectable, debuggable and controllable execution environment for AI agents.

Uindow

uindow

Real browser automation for AI agents. Uindow ships a local MCP server that drives a real, signed Chromium/Electron browser with genuine OS-level input (real cursor movement, real keystrokes, native file dialogs) entirely on the user's own machine.

Pinako AI Bridge is the MCP server that connects Pinako, a Chromium extension for tab, window, library, and bookmark management, to local AI clients (Claude Desktop, Claude Code, Cursor, Windsurf, Cline, Roo Code, Continue.dev, and any HTTP MCP client). Because the bridge runs in

Safari Web Extension + Node.js MCP bridge giving Claude Desktop full control over Safari — navigate, read pages, click elements, fill forms, and manage tabs. No Playwright or WebDriver dependency.

Nullprint

nullprintai

Let Claude Code, Claude Desktop, OpenAI Codex, Kimi and any MCP-capable AI agent create, launch, check and drive browser profiles in Nullprint, the AI antidetect browser. Install with one command.

🌐 MCP Agents

CodeWithHarshAI

MCP Agents is an AI-powered browser automation tool that lets you interact with websites using natural language. Built with Streamlit, OpenAI, and Puppeteer via the Model Context Protocol (MCP), it supports multi-step navigation, interaction, and content extraction—all with simpl

B4n1web

B4N1-com

B4n1Web is an ultra-lightweight agentic browser engine (11MB) for AI agents.

MCP server for parallel browser automation across multiple providers. Run multiple concurrent browser sessions in memory with a shared, provider-agnostic tool surface across Playwright (local Chromium), Browserbase, Anchor Browser, and Cloudflare Browser Run. Each session gets a

Remote browser instances for your AI agents. Reliably complete any browser-based task at scale. Fully-control agentic browsers that spin up in seconds.

WebdriverIO MCP

webdriverio

A Model Context Protocol (MCP) server that enables AI assistants to interact with web browsers and mobile applications using WebDriverIO. Automate Chrome browsers, iOS apps, and Android apps—all through a unified interface.