"A guide to developing Chrome extensions" matching MCP servers:

Enables direct browser control via Chrome DevTools Protocol, supporting navigation, interaction, content extraction, and screenshots through a single MCP tool.

MCP server + Chrome extension that drive the user's real, logged-in Chrome over a local WebSocket. 59 token-efficient web-dev tools: compact element refs instead of screenshots, server-side table filtering, visual regression, accessibility/SEO/security audits, network mocking. Also runs on ChromeOS/Crostini.

Let Claude Code, Codex and any AI agent use the Chrome you're already signed in to. Open-source CLI + MCP server + Chrome extension (native messaging, no debug port); stealth by default.

Connects to a running Chrome instance via CDP to expose browser control as MCP tools, preserving login state, cookies, and extensions for automation.

Enables MCP clients to drive your real Chrome profile through a local, token-protected bridge, so agents can open and navigate tabs, read page snapshots, click, type, scroll, wait, run JavaScript, and take screenshots while keeping your existing logins and extensions. It runs inside the Chrome you already use rather than a separate clean profile.

An MCP server that lets LLM agents control all Chrome browser tabs via accessibility snapshots, element references, and a virtual cursor, supporting operations like click, type, navigate, screenshot, and video recording.

Enables MCP clients to directly operate your existing logged-in Chrome profiles, including cookies and extensions, without re-authentication or a headless browser. It provides tools for managing tabs, navigating, reading pages, clicking, typing, and launching profiles.

Lets several AI clients drive one shared, signed-in Chrome at the same time, giving each session its own background tabs and tab group with per-tab leases so mutations queue while reads overlap. Exposes a full Chrome DevTools-style toolset plus Claude's 31-member browser toolset, along with an HTTP endpoint that turns Messages API tool_use blocks into tool_result blocks.

Enables agents to drive an existing Chrome window by creating tabs, taking snapshots, pressing keys, and filling form fields via native messaging without opening a new browser instance.

Enables AI coding agents to manage Chrome bookmarks and tab groups through MCP, using a sleep-by-default extension that wakes only when tools are called.

Enables browser automation via Chrome, allowing navigation, clicking, typing, screenshotting, and replayable flows for web tasks.

Enables JavaScript-rendered Google searches and readable text extraction from public URLs via a real Chrome instance, along with health and CAPTCHA status monitoring.

An MCP server that reads decrypted cookies from a running Chrome instance via the Chrome DevTools Protocol, returning them in various formats.

Enables reading and writing Chrome bookmarks (folders, URLs, search, move, remove) through MCP clients like Claude Code, using a companion Chrome extension for secure local communication.

Manages Chrome's synced bookmarks through an MCP server and Chrome extension, enabling operations like listing, searching, adding, moving, and deduplicating bookmarks.

Enables AI agents and CLI tools to dispatch downloads through Chrome's native download engine over the MCP protocol, automatically inheriting browser cookies, login sessions, and proxy settings. Supports submitting, monitoring, pausing, resuming, and cancelling download tasks locally without manual server setup.

Lets MCP clients automate a logged-in LINE Chrome extension, enabling chat search, message reading, text sending, and live event streaming for messages and chat updates.

Rust-based MCP server that lets AI agents natively control and debug Chromium browsers via the Chrome DevTools Protocol (CDP). Single pre-compiled binary, installable with npx @raultov/chrome-debug-mcp, Homebrew or one shell command — no Rust toolchain.

Enables AI to interact with Chrome DevTools Protocol to inspect and debug live web pages, including DOM, styles, console logs, and network requests.

A Model Context Protocol (MCP) server for browser automation using Playwright to control Chrome browsers.

Enables AI coding assistants to control and inspect a live Chrome browser for automation, debugging, performance analysis, and screenshot capture through Chrome DevTools.

Exposes Codex's Chrome plugin as an MCP server, enabling MCP clients to drive a real, logged-in Chrome browser by navigating, snapshotting the DOM, clicking, typing, taking screenshots, running Playwright, and sending raw CDP commands.

Enables MCP clients to drive a real Chromium browser for automation, including navigation, JavaScript execution, CDP commands, network capture, and multi-tab control.

Enables AI agents to fully control Google Chrome: navigate, click, fill forms, inspect DevTools, and manage tabs with parallel execution and session isolation.

Enables AI assistants to remotely control TradingView charts in Chrome, including reading charts, writing and fixing Pine Script, managing watchlists and alerts, and capturing screenshots, all through natural language commands.

Exposes a live Chrome browser to any MCP client through a single local endpoint, enabling real-tab control, DOM interaction, cookies and session use, network/console capture, PDF export, and CDP-powered debugging.

Enables AI coding assistants to control a persistent Chrome browser through DevTools Protocol. Supports web navigation, screenshots, element interaction, mobile testing, console logs, and network debugging in a stable Docker environment.

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

A local MCP server that enables Codex to inspect and interact with Chrome tabs through the Chrome DevTools Protocol, primarily for collecting authorized Brightspace course materials into local folders.

MCP server for the LLM Wiki Chrome extension that exposes bounded browser automation tools (shared tabs, accessibility snapshots, screenshots, clicks, typing, etc.) with explicit user consent and strict typing, enabling local agents to interact with specific web pages via a native messaging relay.