"Connecting a Browser" matching MCP servers:

基于百度图片搜索API，支持图片搜索、下载及格式转换的MCP服务器。

Browser-based research MCP server that drives a real Chromium browser via patched Playwright to access JavaScript-rendered content, dynamic tables, and login-walled dashboards. It provides tools for visiting URLs to extract DOM text and screenshots, and for performing structured data extraction using Anthropic Claude Sonnet.

Enables AI agents to control a browser with 30 tools for navigation, interaction, extraction, and tab management, supporting human-like browser automation.

A browser automation tool using Playwright and MCP protocol, enabling agents like OpenClaw or Claude Desktop to control a browser for navigation, content extraction, and interaction.

Multi-instance parallel browser MCP server that manages multiple isolated browser instances in a single Chrome process with automatic login state cloning, allowing parallel independent operations across instances.

A concurrent browser MCP server that supports multiple parallel browser instances

An MCP server that enables AI agents to control a real Chrome browser with full login state through 37 structured automation tools, connecting via the Playwriter extension without needing a remote debugging port.

Enables browser-based Twitter/X research and account workflows through a signed-in browser, supporting search, timeline/profile reads, saved searches, snapshot exports, and prepared account actions without requiring an X developer API key.

An MCP server that provides browser automation capabilities, enabling LLMs to control a web browser for navigation, interaction, and data extraction.

A Model Context Protocol server that combines Playwright browser automation with DevTools-style monitoring capabilities, enabling AI assistants to automate browser tasks and capture network/console logs.

Ultra-fast browser automation server over Chrome DevTools Protocol (CDP), exposed as MCP, enabling AI agents to control a real Chrome browser with low latency and minimal token usage.

Enables controlling a local Chrome browser via MCP tools, using a Chrome extension and WebSocket broker for browser automation.

A Model Context Protocol (MCP) server that provides browser automation capabilities through Vercel's agent-browser, enabling LLMs to interact with web pages using a fast Rust CLI with Node.js fallback.

A universal browser automation server featuring 63 tools for programmatic Chrome control, multi-tab management, and media interaction using Playwright. It enables advanced actions like session recording, performance profiling, and pixel-based interaction through a safe, isolated browser profile.

parallel-browser-mcp is an MCP server for parallel browser automation. It exposes a numeric session model over MCP so one client can create and control multiple browser sessions at the same time across multiple browser providers.

MCP server that drives a user's real Chrome browser via a WebSocket-connected MV3 extension, enabling tab management, navigation, page interaction, screenshots, and script evaluation through natural language.

Implementation of an MCP server for the RAG Web Browser Actor. This Actor serves as a web browser for large language models (LLMs) and RAG pipelines, similar to a web search in ChatGPT.

MCP server for controlling a local camofox-browser instance, enabling LLM agents to perform web automation tasks such as navigation, interaction, snapshotting, and content extraction.

MCP server to control a real Chrome browser from Claude, enabling navigation, DOM snapshots, clicks, typing, screenshots, and JS execution via a Chrome extension bridge.

Enables agents to control a real Chromium browser with semantic tools, providing compact observations and outcome-verified actions for web interaction tasks.