"browser" matching MCP servers:

Enables any agent to drive a dedicated Chromium instance through MCP, including opening and reading pages, taking steps, logging in via a password vault, downloading/uploading files, and replaying saved routines. It also gates sensitive actions behind approvals and can use client certificates or one-time card data for official procedures.

Lets AI agents drive your real, already-logged-in browsers on macOS in the background without stealing focus, organizing work into tab groups, reading pages as compact accessibility snapshots, and saving repeatable scenarios. Supports Chrome, Edge, Brave, Yandex Browser, and Safari, with per-agent isolation and automatic tab cleanup.

Browser use using Typesafe's Jev model

Enables AI agents to open, read, and act on live web pages through verified browser actions, including filling forms, extracting data, debugging pages, and handling bot walls.

Agent-native browser control MCP server that enables AI agents to browse and interact with web pages via accessibility tree snapshots and ref ID-based commands.

A token-efficient MCP server for Chrome browser automation that uses direct CDP and accessibility-tree-based references for stable element selection across DOM changes.

Headed Playwright browser MCP server with persistent profile, providing 23 tools for full browser automation while masking PII data.

Gives AI agents a compact, semantic interface to the browser, returning structured page snapshots with stable element IDs instead of raw DOM. Enables agents to navigate, interact, and extract information from web pages efficiently.

Enables AI agents to drive your real, logged-in Chrome browser with existing sessions and cookies, bypassing CAPTCHA and anti-bot measures, with support for multi-session and human-in-the-loop workflows.

Enables MCP clients to drive a self-hosted Chrome session for browsing tasks through browser tools, while providing a live view URL so a human can take over at prompts like logins or 2FA.

Lets MCP agents drive VS Code's integrated browser tab that the user shares with them: opening pages, taking accessibility snapshots and screenshots, clicking, typing, scrolling, dragging and reading console and network activity with real trusted input. It also maps a picked element back to the source file, line and column that rendered it, so an agent receives the same selection the developer clicked.

Enables coding agents to drive a real, indexed Chrome browser over MCP stdio, navigating pages, observing numbered interactive elements, and performing click, type, and select actions without the server itself calling any model.

Lets any number of concurrent Claude Code sessions drive a Firefox browser through the Browser Control extension by funneling every session's commands over a single shared port via a background daemon and private unix socket. Sessions no longer have to compete for a limited pool of extension ports, and requests stay isolated through per-request correlation ids.

A powerful MCP server for UI designers and developers to extract, analyze, and clone website front-end code (HTML, CSS) with pixel-perfect accuracy using browser automation.

Exposes a headful, collaborative browser over MCP so an agent and a user can share one visible Chromium window: the agent navigates, reads, clicks, types, and fills forms, while the user watches and can take over for passwords, CAPTCHAs, 2FA, and payments, with every action written to an append-only audit trail. It also runs headless under a chat-based harness.

A lightweight 30KB MCP browser automation server that uses raw Chrome DevTools Protocol to enable AI agents to browse the web, take screenshots, interact with elements, and capture live page events like console logs and network requests.

Gives browser agents a reviewed map of 79 real sites — entry URLs, access verdicts, and role/accessible-name button maps for 104 screens — so an agent can find where things are and know whether it may act at all. Safety rules in code halt irreversible actions such as pay, order, submit and delete pending explicit human approval, while per-site memory recalls which routes worked last time.

touch-browser is an evidence-grounded MCP server for public docs and research web workflows. It helps AI agents search and open web pages, extract page-local evidence with citations and confidence bands, classify browsing risk, and synthesize multi-page sessions into citation-ready reports.

An MCP server that enables AI coding tools to control a browser for automated actions, UI extraction, network interception, and screenshots.

A headless browser MCP server that allows AI agents to fetch web content and perform Google searches without API keys, supporting various output formats like Markdown, JSON, HTML, and text.