MCP Chrome Google Search
The MCP Chrome Google Search server enables Google searches and webpage content extraction through Chrome browser automation.
Perform Google Searches: Search with optional site filters, timeframe filters (hour, day, week, month, year), and retrieve specific pages of results (up to page 5, ~10 results per page).
Fetch Webpage Content: Extract readable text content from any URL, optionally including links.
Authenticated Access: Access authenticated content via your Chrome browser through visible browser windows and tabs.
Allows searching Google and extracting search results to provide information to Claude
Uses Chrome browser to perform web searches and extract webpage content for Claude
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@MCP Chrome Google Search search for the latest AI research papers on arXiv"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
MCP Chrome Google Search Tool
MCP tool for Google search and webpage content extraction using Chrome browser. Works with Claude to enable Google search and content fetching capabilities.
Quick Installation
Configure Claude Desktop
Open Claude Desktop on Mac
Go to Claude > Settings > Developer > Edit Config
Add the following to your config file:
{ "mcpServers": { "mcp-chrome-google-search": { "command": "npx", "args": [ "-y", "@cmann50/mcp-chrome-google-search" ] } } }Restart Claude Desktop
First Time Setup
Grant Accessibility Permissions
On first run, approve macOS accessibility permissions prompt
Navigate to: System Preferences > Security & Privacy > Privacy > Accessibility
Add and enable permissions for your terminal app
Enable Chrome JavaScript from Apple Events
Open Chrome
Navigate to: View > Developer > Allow JavaScript from Apple Events
One-time setup only
Once configured, Claude will be able to perform Google searches and extract webpage content through Chrome when you make requests.
Related MCP server: Google Search MCP
Key Advantages
Free to search google
Opens and small windows and uses your chrome browser, so should not get blocked
Since it is using your Chrome window it can access authenticated content. Claude can just open the URL in your browser.
Platform Support
✅ macOS
❌ Windows (not supported)
❌ Linux (not supported)
Requirements
macOS
Google Chrome
Node.js 20 or higher
Alternative Installation Methods
NPX Installation
npx mcp-chrome-google-searchCustom Installation
Checkout from git
Run
npm run buildAdd to Claude config (use absolute path):
{
"google-tools": {
"command": "node",
"args": [
"/your/checkout/path/mcp/mcp-chrome-google-search/dist/index.js"
]
}
}Local development
To test changes locally bump package.json version and run to put it in edit mode:
npm install -g .Then just do npm run build and the files will go in dist where claude is monitoring
Then press ctrl-R in claude desktop, no need to restart it
Debugging
Log Monitoring
# Follow logs in real-time
tail -n 20 -F ~/Library/Logs/Claude/mcp*.logDev Tools Access
Enable developer settings:
echo '{"allowDevTools": true}' > ~/Library/Application\ Support/Claude/developer_settings.jsonOpen DevTools: Command-Option-Shift-i in Claude desktop
Use ctrl-r in Claude desktop while tailing for better errors
Troubleshooting
Chrome JavaScript Error
If you see:
execution error: Google Chrome got an error: Executing JavaScript through AppleScript
is turned off. For more information: https://support.google.com/chrome/?p=applescript (12)Solution:
Open Chrome
View > Developer > Allow JavaScript from Apple Events
Accessibility Permission Issues
If Chrome control fails:
Open System Preferences
Security & Privacy > Privacy > Accessibility
Ensure terminal app is listed and enabled
Use lock icon to make changes if needed
Implementation Details
Uses AppleScript for Chrome control
Visible automation - Chrome windows will open/navigate
Each request opens a new Chrome tab
Close unused tabs periodically for optimal performance
Only use with trusted Claude instances (has Chrome control access)
Support
Create GitHub issues for problems
Include macOS and Chrome version details
License
MIT License - see LICENSE file for details
Available Tools
2 toolsweb_fetchC
Extract readable text content from a webpage using Chrome browser automation.
Key Features:
Returns main content text and optionally links
Inputs: url (required), includeLinks.
web-searchA
Search webpages and get a specific page of results (each page has ~10 results). Optionally filter by site and timeframe.
Inputs: query_text (required), pageNumber, site, timeframe.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 2 tools
The two tools have clearly distinct purposes: web_fetch extracts content from a specific webpage, while web_search performs web searches and returns result pages. There is no overlap in functionality, making it easy for an agent to choose the correct tool based on the task.
Both tool names follow a consistent snake_case pattern with a clear verb-noun structure: web_fetch and web_search. The naming is predictable and readable, with no deviations in style or convention.
With only 2 tools, the server feels thin for a Google Search domain, which typically involves more operations like advanced filtering, image search, or history management. While the tools cover basic fetch and search, the scope is limited and could benefit from additional functionality to fully represent the domain.
The tools cover core search and content extraction, but there are notable gaps for a Google Search server, such as no tools for image search, news search, or handling search settings. Agents can perform basic tasks but may encounter dead ends for more advanced operations, indicating incomplete coverage of the domain.
Maintenance
Related MCP Connectors
Hosted browser for agents: open pages, search the web, extract data, read PDFs and take screenshots.
Web search, data extraction and controlled browser automation for AI assistants via OAuth.
Give AI agents a real cloud Chrome: open sessions, navigate, read pages, click, type and screenshot.
Control your Chrome from chat: open websites, read what's on the page, click buttons, and fill in f…
Related MCP Servers
- AlicenseNot gradedqualityDmaintenanceEnables web searching through Google, DuckDuckGo, and Bing using a headless Chrome browser, returning structured results with titles, URLs, and snippets. Also supports fetching and extracting text content from any webpage.16MIT
- AlicenseBqualityNot gradedmaintenanceEnables Large Language Models to perform real-time web searches using Google Custom Search API. Integrates with Claude Desktop to retrieve current information from the internet.21MIT
- AlicenseBqualityBmaintenanceUse your signed-in Chrome through a local MCP server and companion extension. Supports tabs, navigation, forms, screenshots, and page reading, with a deny-all domain allowlist. Install: npx -y mcp-browser-extension@latest.22177 npm6MIT
- FlicenseNot gradedqualityCmaintenanceProvides a direct bridge between Claude and an authenticated Chrome session, enabling fetch requests with session cookies and JavaScript execution within live web pages.-