"Automating Browser Operations with Scripting or Tools" matching MCP servers:

Persistence, headed Chromium browser control for MCP clients like OpenCode and Claude Code, enabling navigation, inspection, clicking, filling, and human-gated actions on JavaScript-heavy or login-walled pages.

Reliable, scalable browser infrastructure for AI agents. Route, pool, and failover across any browser provider. 8 built-in browser tools using raw Chrome CDP - navigate, screenshot, snapshot, interact, evaluate. Zero-config with auto Chrome detection & concurrent sessions support

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.

Enables AI agents to inspect and modify Chrome state directly through extension APIs, listing tabs and windows and moving or reordering tabs within and across windows. Operations are validated and never simulate mouse/keyboard input, steal focus, or activate tabs implicitly.

Enables agents to observe and act on live browser pages through screenshots, bounded actions, responsive captures, console and network inspection, tab operations, and session management over local stdio or authenticated HTTP.

Exposes a real, visible Electron browser to agents through 17 browse_* tools so they can navigate pages, read them as a structured semantic tree (role/label/value/states/actions), and click or type by element id — no screenshots, OCR, or coordinate guessing — with humans able to take over the same window at any time.

MCP server that lets agents drive your real Chrome browser with existing logins and sessions via an outbound-only WebSocket extension. It exposes Playwright-compatible browser tools for navigation, clicking, typing, and snapshots.

MCP server for managing and controlling multiple isolated Chrome/Edge browser instances, exposing tools for navigation, screenshots, clicking, form filling, and JavaScript execution to AI clients.

Enables AI agents to control a real, persistent Chrome browser over MCP, perceiving pages as accessibility trees and interacting with elements by their accessible names without automation fingerprints or site-specific glue.

Gives MCP-compatible AI agents direct control of your real browser with existing sessions, logins, and cookies. Supports multiple agents concurrently with tab targeting.

Enables an agent to drive a real browser while enforcing provenance-based gating so URLs and form values must trace to the user or an allowlist, never to untrusted page content.

Real Chrome for AI agents: drive a signed-in browser through 32 MCP tools, with a person able to watch and take over. Runs as the Oya desktop app on a laptop or as a hosted cloud endpoint.

Enables LLM clients to drive a real browser one outcome at a time, with the TypeSafe System One model choosing the element, action and value while Playwright performs the action, and with the LLM never needing to read page snapshots unless it takes over. Exposes tools for navigation, goal-directed actions, yes/no page checks, option choosing, page reading, compact snapshots, direct actions, screenshots and invoking a page's own WebMCP tools.

Enables agents to control a visible Chromium browser via Playwright with tools for tabs, page reading, element finding, form input, mouse/keyboard actions, screenshots, console/network inspection, JavaScript execution, viewport emulation, and batched calls.

Fast Browser is an MCP server that lets Claude Code and Codex drive an existing Chrome browser with your real profile, logins, and tabs, using a macro library for multi-step flows in single tool calls and supporting concurrent agents with isolated tab groups.

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.

Exposes browser tabs to any MCP client through a local broker, letting agents discover pages, take text snapshots with numbered elements, and drive them via click, type, navigate, eval, network/log inspection, and screenshots. Supports stdio, Streamable HTTP, and SSE transports so IDE and CLI agents can orchestrate browser automation.

MCP server for local browser control via Chrome/Edge extension, enabling agents to open isolated tabs, observe pages, take screenshots, and interact with accessible controls using an existing browser profile. It is agent-agnostic, local-only, and supports safe session scoping with origin grants and sensitive-data blocking.

Enables LLM clients like Claude to drive a real Playwright browser by stating one outcome at a time, while a TypeSafe Jev model decides which element, action, and value to use each round, returning a status of done, stuck, or needs-confirmation. Also exposes tools for direct element actions, page checks, snapshots, text reading, screenshots, and calling a page's own WebMCP tools.

Enables an MCP client to drive a live browser toward one outcome per step, with page state described in code and a fast model call deciding the target element, action, value, and whether the step is done, blocked, or irreversible. Supports page reading, snapshots, checks, screenshots, direct actions, and calling tools a page exposes via WebMCP.

A plugin that allows Dify to connect to multiple MCP (Model Control Protocol) servers using HTTP with Server-Sent Events transport, supporting custom configurations for URLs, headers, and timeouts.

A MCP server that allows AI assistants to interact with the browser, including getting page content as markdown, modifying page styles, and searching browser history.

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.

Enables MCP clients to drive a sandboxed Chromium container over CDP with tools for navigation, clicking, typing, selecting, key presses, scrolling, finding, text extraction, snapshots, and screenshots, optionally restricted by a host allowlist.

Lets OpenCode check whether Arc is open on Windows and navigate it to absolute HTTP(S) URLs from WSL2, even when another browser is the Windows default.

Enables web ChatGPT to drive durable, sandboxed Claude Code sessions on a local Mac, with controlled read, modify, verify, and recover operations via six session control tools.

Enables AI assistants to browse the web efficiently via compact goal-based views, lazy image loading, and low-latency interactions.

An MCP server that gives an agent a remote browser:

MCP server providing browser automation for AI agents, enabling actions like clicking and typing, structured data extraction, content validation, multi-step task execution, and memory enrichment from web pages.

Use your existing Firefox and logged-in tabs, limited to tabs or tab groups you explicitly share.

Human-in-the-loop automation framework. Log them in, watch them run.

Enables AI assistants to control a web browser through Playwright-compatible tools, with an on-device decision engine for autonomous task completion and optional LLM escalation.

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 Grok CLI to control your already-running Brave browser via Chrome DevTools Protocol, allowing tab management, clicking, typing, navigation, and screenshots using your existing session and logins.

Enables AI agents to reliably control Chrome or Edge through MCP using semantic snapshots and ref-based actions. Provides self-healing browser reconnection, session recovery, and resilient interaction fallbacks.

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 Model Context Protocol (MCP) integration that provides Claude Desktop with autonomous browser automation capabilities. This agent enables Claude to interact with web content, manipulate DOM elements, execute JavaScript, and perform API requests.