Server facts
concurrent-browser-mcp
Project
- Author
- sailaoda
- License
- Not specified
- Category
- Browser Automation
Tech
- Runtime / language
- Not specified
- Transports
- stdio
- Remote available
- No
- Authentication
- Not specified
Activity
- GitHub stars
- 12
- Last commit
- Data as of
Tags
- browser
- concurrent
- parallel
Overview
Parallel browser sessions are the focus of concurrent-browser-mcp, which connects MCP clients to Playwright-based automation through stdio. Clients can create and list instances, direct actions to a particular instance, and close individual browsers or all instances together. Chromium, Firefox, and WebKit are supported. Configuration covers instance limits, timeout and cleanup intervals, browser selection, headless operation, viewport dimensions, and user agents. Timed-out instances are cleaned up automatically, making lifecycle management part of the same workflow as page automation.
Within each instance, tools handle navigation, history movement, refreshes, clicks, text entry, form filling, and dropdown selection. Clients can wait for elements or navigation before continuing, then inspect element text and attributes, retrieve page information with HTML and metadata, or capture page and element screenshots. A Markdown extraction tool provides page content for language-model use, while JavaScript evaluation supports execution in the page context. The documented concurrency example creates several instances and navigates them to different pages in parallel, illustrating how separate browsing tasks can be coordinated through the available tools.
concurrent-browser-mcp setup notes
- concurrent-browser-mcp records stdio only; confirm a network transport upstream before planning remote access.
- concurrent-browser-mcp has no recorded license; confirm reuse terms in its repository.