Server profile

Browser MCP

Browser MCP combines an MCP server with a Chrome extension to automate your existing browser. It is aimed at AI applications that need local browsing and access to already signed-in sessions.

Server facts

Browser MCP

Project

License
Apache-2.0

Tech

Runtime / language
node
Transports
stdio
Remote available
No
Authentication
Not specified

Activity

GitHub stars
7,189
Last commit
Data as of

Tags

  • Browser Automation
  • Chrome Extension
  • Existing Sessions
  • Local Execution

Overview

Browser MCP connects AI applications to the browser a user already has, pairing an MCP server with a Chrome extension. The README names VS Code, Claude, Cursor, and Windsurf as examples of applications that can use it. Its central distinction is profile reuse: automation operates through the existing browser rather than launching a separate browser instance. That preserves signed-in sessions across services and brings the user's real browser fingerprint into the automation workflow. The project presents this as a way to reduce the basic bot-detection obstacles associated with fresh automated browser sessions, not as a documented guarantee for every website.

Local operation is another stated focus. The README says browser activity stays on the device rather than being sent to remote servers by the automation system, and it attributes lower interaction latency to that local execution. The repository was adapted from Microsoft's Playwright MCP implementation specifically to work with the user's browser. However, the supplied README is a brief project introduction rather than a complete setup guide. It links to external documentation but gives no runnable installation command, environment-variable configuration, or named tool inventory. It also warns that the repository cannot currently build independently because it depends on utilities and types held in the development monorepo.

Install & configure

Requirements

  • Chrome with the Browser MCP extension
  • A compatible AI application or MCP client

No install command stated in the README — see repo.

A runnable installation command is Not stated in the README. It links to https://docs.browsermcp.io for setup and notes that the repository cannot build independently because of monorepo dependencies.

Config file · macOS: ~/Library/Application Support/Claude/claude_desktop_config.json

Windows: %APPDATA%\Claude\claude_desktop_config.json

Use Settings → Developer → Edit Config when available. Do not assume a Linux configuration path; check the client documentation for your platform. Remote servers use the app’s connector flow when supported, not the local stdio file shown here. Merge this example with existing settings; do not overwrite unrelated servers.

No install command stated in the README — see repo. Check the client documentation for a supported connection method.

Read the Claude Desktop setup guide

Config file · Project: .cursor/mcp.json

User: ~/.cursor/mcp.json

The project path is relative to the workspace root. The tilde denotes your user home directory. Use Cursor’s MCP settings to confirm which configuration and scope your installed version is reading. Merge this example with existing settings; do not overwrite unrelated servers.

No install command stated in the README — see repo. Check the client documentation for a supported connection method.

Read the Cursor setup guide

Config file · Workspace: .vscode/mcp.json

For user scope, use the “MCP: Open User Configuration” command if available. Do not guess a user configuration path across operating systems, profiles, containers, or remote workspaces; check the client documentation. Merge this example with existing settings; do not overwrite unrelated servers.

No install command stated in the README — see repo. Check the client documentation for a supported connection method.

Read the VS Code setup guide

Config file · macOS/Linux: ~/.codeium/windsurf/mcp_config.json

Windows: %USERPROFILE%\.codeium\windsurf\mcp_config.json

Open the MCP configuration through Windsurf’s settings when possible to confirm the active file. Paths can differ in managed or future releases; check the client documentation if this location is not present. Merge this example with existing settings; do not overwrite unrelated servers.

No install command stated in the README — see repo. Check the client documentation for a supported connection method.

Read the Windsurf setup guide

Config file · Project scope: .mcp.json at the repository root

The project file uses mcpServers. For user scope, use claude mcp add --scope user rather than assuming .mcp.json in your home directory is the user configuration. Check the client documentation for managed settings and storage details. Merge this example with existing settings; do not overwrite unrelated servers.

No install command stated in the README — see repo. Check the client documentation for a supported connection method.

Read the Claude Code setup guide

Examples are translated from the published configuration. Supply your own credentials and verify requirements in the upstream README. Remote connectors are shown only where a supported configuration format is known.

Tools

No individual tool names were confirmed in the source material. Check the repository for its current tool list.

Names, permissions, and defaults can change. Check the current upstream documentation before granting access.

Use cases

  • Automate a browser session that is already signed into services.
  • Connect browser actions to an AI editor or assistant.
  • Use an existing browser profile instead of a fresh automated instance.

Strengths

  • Reuses existing profile state and logged-in sessions.
  • Describes local execution without remote browser-activity storage.
  • Designed to work with several AI applications.

Limitations

  • The repository cannot currently be built independently of its development monorepo.
  • No runnable installation command or tool inventory is stated in the README.

Frequently asked questions

The README says it automates the user’s existing browser profile instead of creating new browser instances.

Yes. Profile reuse is described as retaining existing service logins.

The README explicitly says the repository cannot yet build by itself because it relies on monorepo utilities and types.

Not stated in the README. The supplied text points to the Browser MCP documentation for setup.

Independent listing, not an affiliation or security review. Grant the least access needed and verify the upstream instructions before running code.

Related MCP servers

IDA Pro MCP

Security & Reverse Engineering

IDA Pro MCP connects AI clients to IDA for binary inspection, decompilation, database changes, and optional debugging. Its recommended headless path manages persistent analysis workers and explicit database sessions.

Playwright MCP

Browser Automation

Playwright MCP lets AI assistants operate browsers using structured accessibility data. It suits agents that need persistent page context, interactive exploration, and browser inspection without a vision model.

Browserbase MCP Server

Browser Automation

Browserbase MCP Server lets assistants operate cloud browser sessions through Browserbase and Stagehand. Six tools handle sessions, navigation, page actions, observation, and extraction, with hosted and self-hosted connection options.

BrowserTools MCP

Browser Automation

BrowserTools MCP brings browser logs, screenshots, selected elements, and Lighthouse audits into compatible AI editors. It uses a Chrome extension plus two local servers, and the project is no longer active.

Playwright MCP Server

Browser Automation

ExecuteAutomation’s Playwright MCP Server lets AI clients automate real browsers, capture screenshots, scrape pages, and generate tests. It also provides device-profile emulation and local stdio or standalone HTTP operation.

Browser Use MCP Server

Browser Automation

Browser Use MCP Server connects AI agents to browser-use for browser control. It supports SSE and proxied stdio connections, asynchronous tasks, and VNC viewing so users can watch browser automation as it happens.

Hyperbrowser MCP Server

Browser Automation

Hyperbrowser MCP Server combines web scraping, crawling, structured extraction, and cloud browser agents. Assistants can choose Browser Use, OpenAI computer use, or Claude computer use and manage persistent profiles.