Concurrent Browser Mcp

Created By
sailaodaa year ago
A concurrent browser MCP server that supports multiple parallel browser instances.
Overview

What is Concurrent Browser MCP?

Concurrent Browser MCP is a server that supports multiple parallel browser instances, built on Playwright, allowing for efficient browser automation.

How to use Concurrent Browser MCP?

To use Concurrent Browser MCP, install it via npm or clone the repository, then start the server using the command npx concurrent-browser-mcp with optional configurations for instance management.

Key features of Concurrent Browser MCP?

  • 🚀 Multi-instance concurrency: Supports running multiple browser instances simultaneously.
  • 🎯 Instance management: Dynamically create, manage, and clean up browser instances.
  • 🔧 Flexible configuration: Supports various browser types and custom configurations.
  • 🛡️ Resource management: Automatically cleans up timed-out instances to prevent resource leaks.
  • 🌐 Full automation support: Complete browser automation features including navigation, clicking, inputting, and screenshotting.
  • 💻 Cross-platform: Supports Chromium, Firefox, and WebKit.

Use cases of Concurrent Browser MCP?

  1. Running automated tests across multiple browsers in parallel.
  2. Web scraping tasks that require simultaneous data extraction from different sites.
  3. Load testing web applications by simulating multiple users.

FAQ from Concurrent Browser MCP?

  • Can I run multiple browsers at the same time?

Yes! Concurrent Browser MCP allows you to run multiple browser instances concurrently.

  • Is it easy to set up?

Yes! You can install it via npm or clone the repository and follow the setup instructions.

  • What browsers are supported?

It supports Chromium, Firefox, and WebKit.

Server Config

{
  "mcpServers": {
    "concurrent-browser-mcp": {
      "command": "npx",
      "args": [
        "concurrent-browser-mcp",
        "--max-instances",
        "20"
      ]
    }
  }
}
Project Info
Hosted
Created At
a year ago
Updated At
10 months ago
Author Name
sailaoda
Star
-
Language
-
License
-

Recommend Servers

View All
Bring your real authenticated browser session to AI coding agents. Local-first MCP server + Chrome MV3 extension. No cloud. No telemetry.
@Cubenest

peek records the user's actual logged-in browser (DOM via rrweb, console events, network metadata, optional response bodies via opt-in Deep capture) through a Chrome MV3 extension. The extension ships events through a native-messaging stdio bridge to a local MCP server (peek-mcp), which persists them to a SQLite database at ~/.peek/sessions.db. AI coding agents (Claude Code, Cursor, Cline, Windsurf) read sessions from the database via 10 MCP tools: Tool What it does list_recent_sessions List recently recorded sessions (id, origin, ts, event count). get_session_summary LLM-readable narrative summary of a session. get_session_console_errors Console errors recorded in a session. get_session_network_errors Failed/notable network requests in a session. get_user_action_before_error Last N user actions before a console error. generate_playwright_repro Generate a runnable Playwright test from a session. get_dom_snapshot Reconstruct the DOM at a given timestamp. query_dom_history Timeline of attribute/text changes for a selector. request_authorization Side-panel consent for write actions (Level 3). execute_action Dispatch a UI action (gated by permission level + destructive blocklist). Why local-first matters Every other "browser session for AI" tool ships to a vendor cloud. peek's SQLite + extension live on the user's machine — no remote endpoints, no telemetry. The privacy policy (docs/peek/PRIVACY_POLICY.md) is the source of truth. Install # 1. Add the MCP server to Claude Code claude mcp add peek -- npx -y @peekdev/mcp # 2. Install the Chrome extension from the Chrome Web Store # (link added once the CWS listing is approved)

a day ago