search_google
Search Google for a query
LABSCO SUMMARY
Three tools, and the session is what makes them add up to research.
Because every query, page and screenshot lands in one accumulating session, a long piece of research keeps its trail — you can ask what was already read and get a list rather than a guess, and the bundled agentic-research prompt pushes for a URL beside every claim. Set expectations accordingly: the author calls the code pre-alpha, and steering it toward named sources ("from Reuters or AP") gets noticeably better material than a bare topic.
What it is
A three-tool browser research server. It drives Playwright to run a Google search, open a result and pull its content out, and it exposes the screenshots and the running session as MCP resources.
What you get
- search_google runs a query and extracts the results, so the model works from a live result page rather than what it remembers
- visit_page opens a URL and extracts the page content, with takeScreenshot capturing the page at the same time
- take_screenshot captures the current page on its own
- Screenshots are saved as MCP resources and reachable in Claude Desktop through the paperclip icon
- A research session accumulates the queries, the pages visited, the content extracted, the screenshots and their timestamps
- An agentic-research prompt ships with the package: broad searches first, authoritative sources preferred, direction refined as findings come in, and every claim cited with its URL
Requirements
No account and no key. Node.js 18 or higher, and it starts as npx -y @mzxrai/mcp-webresearch@latest; Playwright comes with it as a dependency, so the browser it drives is installed for you. macOS is the platform the author lists as verified — Linux is not yet ticked. MIT.
Setup effort
One command — npx -y @mzxrai/mcp-webresearch@latest
USE CASES
01
Answering a question that depends on what is true this week
Search, open the results that look authoritative, and pull their text in — the answer comes from pages fetched during the conversation.
02
Keeping a citation trail through a long research session
Each query and page joins the session with a timestamp, so the sources behind an answer can be listed rather than reconstructed.
03
Capturing what a page looked like, not just what it said
Screenshot the page as you visit it — pricing tables, dashboards and layouts survive as images rather than as flattened text.
04
Comparing a handful of vendors or sources side by side
Run the searches, visit each candidate in turn, and let the session hold what each one said so the comparison is drawn from the pages themselves.
3 tools
Counted once with only startup setup. Other versions, modes or optional credentials may expose a different list.
take_screenshot
Take a screenshot of the current page
visit_page
Visit a webpage and extract its content
BEFORE YOU INSTALL
What to know first
Tools you get
3 tools when we connected. Agentic-research is a prompt and takeScreenshot is an argument of visit_page, not tools. Captured screenshots and the research session are available as MCP resources.
Requires
- npx on PATH
- Node.js >= 18
Where it runs
The documented client runs the server on your machine.
CONTEXT COST
Light Standing cost
Rated by the size of the 3 tool definitions that ride along on every turn, not by how many there are
INSTALLATION
Connect your client
Server setup
TERMINAL
npx -y @mzxrai/mcp-webresearch@latestMCP Clients
Claude Desktop
CLAUDE DESKTOP · JSON
{
"mcpServers": {
"webresearch": {
"command": "npx",
"args": [
"-y",
"@mzxrai/mcp-webresearch@latest"
]
}
}
}
