MCP.directory
Browser MCP

Browser MCP

djyde

Browser extension and MCP server that lets you interact with your current browser tab, extracting content as markdown and modifying page styling. Works with the browser you're actively using rather than launching a separate browser instance.

Browser extension that enables real-time interaction with web pages, allowing retrieval of content as markdown, CSS styling modifications, and browser history searches.

83523 views15Local (stdio)
browser automation
GitHub

What it does

  • Extract current page content as markdown
  • Modify page CSS styling in real-time
  • Search browser history
  • Interact with actively browsed web pages

Best for

Summarizing and analyzing web contentApplying custom styling to web pagesResearch workflows requiring browser history searches
Works with your active browser sessionReal-time page modificationsBrowser extension based

About Browser MCP

Browser MCP is a community-built MCP server published by djyde that provides AI assistants with tools and capabilities via the Model Context Protocol. Discover Browser MCP on the Chrome Web Store—a powerful Chrome extension for real-time web interaction, markdown, CSS ch It is categorized under browser automation.

How to install

You can install Browser MCP in your AI client of choice. Use the install panel on this page to get one-click setup for Cursor, Claude Desktop, VS Code, and other MCP-compatible clients. This server runs locally on your machine via the stdio transport.

License

Browser MCP is released under the MIT license. This is a permissive open-source license, meaning you can freely use, modify, and distribute the software.

browser-mcp

A browser extension and MCP server that allows you to interact with the browser you are using.

mcp

jkXeswNy@2x

Usage

{
  "mcpServers": {
    "playwright": {
      "command": "npx",
      "args": [
        "@djyde/mcp-browser@latest"
      ]
    }
  }
}

Tools

All available tools are listed in server/src/tools.ts.

get_current_page_markdown

Get the markdown from current browser browsing page.

example:

Summarize the current page.

append_style

Append a css style to the current browser browsing page.

example:

Change the current page to dark mode.

history_search

Search the browser history.

example:

Search the browser history for "github".

Roadmap

  • Publish the extension to extension store.
  • Write documentation.
  • Add more tools.

Build

pnpm i

Extension

cd extension

# chrome
npm run build

# edge
npm run build:edge

# firefox
npm run build:firefox

After building, the extension will be in the extension/.output directory.

Server

cd server

# dev
npm run dev

# build
npm run build

server/dist/cli.js is the MCP server entry.

Contributing

Add a new tool

  1. Add the tool schema to the tools array in server/src/tools.ts.
  2. Add a extension callable handler in extension/calls.ts.
  3. Add a tool handler in server/src/tools.ts. Use the call function to call the extension handler.

License

AGPL-3.0-or-later

Alternatives

Firecrawl

Firecrawl

mendableai
89.6k

Unlock AI-ready web data with Firecrawl: scrape any website, handle dynamic content, and automate web scraping for resea

OfficialPopular
3.0k125
Browser Use

Browser Use

browser-use
79.9k

Browser Use lets LLMs and agents access and scrape any website in real time, making web scraping and web page scraping e

OfficialPopular
36616
Playwright Browser Automation

Playwright Browser Automation

microsoft
28.4k

Enhance software testing with Playwright MCP: Fast, reliable browser automation, an innovative alternative to Selenium s

OfficialPopular
7.6k545
Chrome DevTools MCP

Chrome DevTools MCP

chromedevtools
28.1k

AI-driven control of live Chrome via Chrome DevTools: browser automation, debugging, performance analysis and network mo

OfficialPopular
50711

Related Skills

Browse all skills
notebooklm

Query Google NotebookLM for source-grounded, citation-backed answers from uploaded documents. Reduces hallucinations through Gemini's document-only responses. Browser automation with library management and persistent authentication.

144
dev-browser

Browser automation with persistent page state. Use when users ask to navigate websites, fill forms, take screenshots, extract web data, test web apps, or automate browser workflows. Trigger phrases include "go to [url]", "click on", "fill out the form", "take a screenshot", "scrape", "automate", "test the website", "log into", or any browser interaction request.

45
chrome-devtools

Browser automation, debugging, and performance analysis using Puppeteer CLI scripts. Use for automating browsers, taking screenshots, analyzing performance, monitoring network traffic, web scraping, form automation, and JavaScript debugging.

30
qa-tester

"Browser automation QA testing skill. Systematically tests web applications for functionality, security, and usability issues. Reports findings by severity (CRITICAL/HIGH/MEDIUM/LOW) with immediate alerts for critical failures."

25
browser-automation

Automate web browser interactions using natural language via CLI commands. Use when the user asks to browse websites, navigate web pages, extract data from websites, take screenshots, fill forms, click buttons, or interact with web applications. Triggers include "browse", "navigate to", "go to website", "extract data from webpage", "screenshot", "web scraping", "fill out form", "click on", "search for on the web". When taking actions be as specific as possible.

23
playwright-browser-automation

Complete browser automation with Playwright. Auto-detects dev servers, writes clean test scripts to /tmp. Test pages, fill forms, take screenshots, check responsive design, validate UX, test login flows, check links, automate any browser task. Use when user wants to test websites, automate browser interactions, validate web functionality, or perform any browser-based testing.

20