Spring AI Chrome

Provides browser automation through MCP to control Chrome, perform searches, fetch data, and summarize content across multiple tabs.
  • other

2

GitHub Stars

other

Language

6 months ago

First Indexed

2 months ago

Catalog Refreshed

Documentation & install

Readme and setup notes from the catalogue, plus a client-ready config you can copy for your MCP host.

Installation

Add the following to your MCP client configuration file.

Configuration

View docs
{
  "mcpServers": {
    "qoxogus-spring-ai-chrome-mcp-server": {
      "command": "/Users/baetaehyeon/Library/Java/JavaVirtualMachines/corretto-21.0.5-1/Contents/Home/bin/java",
      "args": [
        "-Dspring.ai.mcp.server.stdio=true",
        "-jar",
        "/Users/baetaehyeon/dev/chrome-mcp-server/build/libs/chrome-mcp-server-0.0.1.jar"
      ]
    }
  }
}

The Spring AI Chrome MCP Server lets you control a Chrome browser instance from an MCP client. You can open browsers and tabs, perform searches, visit pages, take actions, and extract content across multiple tabs, all through a standardized MCP interface. This makes it easy to automate browsing tasks, summarize pages, fetch live data, and integrate browser capabilities into your workflows.

How to use

You connect an MCP client to the Spring AI Chrome MCP Server to issue browser-related commands. Use the available actions to manage multiple browsers and tabs, navigate to URLs, perform searches, click links by visible text, capture screenshots, and read or extract page text. Typical workflows involve opening a browser (or multiple), opening new tabs, visiting pages, performing targeted searches, and summarizing or extracting content for your AI-assisted tasks.

How to install

Prerequisites: you need a Java runtime installed on your system. The server runs as a stdio MCP server using a Java command to launch the jar file.

{
  "mcpServers": {
    "spring_ai_chrome_mcp_server": {
      "command": "/Users/baetaehyeon/Library/Java/JavaVirtualMachines/corretto-21.0.5-1/Contents/Home/bin/java",
      "args": [
        "-Dspring.ai.mcp.server.stdio=true",
        "-jar",
        "/Users/baetaehyeon/dev/chrome-mcp-server/build/libs/chrome-mcp-server-0.0.1.jar"
      ]
    }
  }
}

How to run the server locally

  1. Ensure Java is installed and the java command is available in your PATH.

  2. Save the MCP server configuration to a file named claude_desktop_config.json (or use the exact structure shown in the snippet above).

  3. Start the MCP server using the full java command and jar path from the configuration.

  4. Connect your MCP client to the server endpoint provided by the runtime (the client uses the stdio channel defined in the config).

Available tools

open_browser

Open a new browser instance or bring focus to an existing one. If none are configured, the default browser opens.

open_browser_by_browser_id

Open a browser by its ID to manage multiple concurrent browser instances.

google_search

Perform a Google search in the active browser tab using the given query text.

google_search_by_browser_id

Perform a Google search in the specified browser by its ID.

navigate_to_url

Navigate the active tab to a specified URL.

navigate_to_url_by_browser_id

Navigate a specific browser's active tab to a given URL by ID.

click_link_with_text

Click a link in the current page that matches the visible link text.

click_link_with_text_by_browser_id

Click a link by text in the specified browser by ID.

take_screenshot

Capture a screenshot of the current active page in the active browser.

take_screenshot_by_browser_id

Capture a screenshot in the specified browser by its ID.

get_page_title

Retrieve the title of the current page in the active tab.

get_page_title_by_browser_id

Retrieve the title of the page in the specified browser by its ID.

input_text

Enter text into the currently focused input field in the active tab.

input_text_by_browser_id

Enter text into the focused field in the specified browser by ID.

extract_page_text

Extract visible text from the current page in the active tab.

extract_page_text_by_browser_id

Extract text from the current page in the specified browser by ID.

get_cookies

Retrieve cookies from the current page in the active tab.

get_cookies_by_browser_id

Retrieve cookies from the current page in the specified browser by ID.

open_new_tab

Open a new tab in the active browser.

open_new_tab_by_browser_id

Open a new tab in the specified browser by ID.

open_new_tab_with_url

Open a new tab and navigate to a given URL.

open_new_tab_with_url_by_browser_id

Open a new tab in the specified browser by ID and navigate to a URL.

close_current_tab

Close the currently active tab in the active browser.

close_current_tab_by_browser_id

Close the currently active tab in the specified browser by ID.

switch_to_tab

Switch focus to a tab by index in the active browser.

switch_to_tab_by_browser_id

Switch focus to a tab by index in the specified browser by ID.

get_tab_list

List all open tabs in the active browser.

get_tab_list_by_browser_id

List all open tabs in the specified browser by ID.

close_all_tabs_except_current

Close all tabs except the currently active one in the active browser.

close_all_tabs_except_current_by_browser_id

Close all tabs except the current one in the specified browser by ID.

close_browser

Close the active browser window.

close_browser_by_browser_id

Close the specified browser by ID.

close_all_browsers

Close all opened browsers.

Built by
VeilStrat
AI signals for GTM teams
© 2026 VeilStrat. All rights reserved.All systems operational