MCP SERVERSearch Google, open the results, extract the content and keep a screenshotted record of where each answer came from.
LABSCO SUMMARY
The session resource is the part worth having: every query, page and screenshot with a timestamp, so a research pass can be retraced instead of reconstructed. If you skip the bundled research prompt, name the sources you want in the request — 'from Reuters or AP' rather than just 'news today' — because the quality of the search terms decides the quality of everything downstream.
A fork of mzxrai/mcp-webresearch, the small web-research server built on Playwright: it runs the search, visits the pages, pulls out the content, and keeps the whole pass as a session you can refer back to. The fork reworks Google search, which its README says no longer gets CAPTCHA-blocked, and adds a Google Scholar search tool, search_scholar.
Node.js 18 or later, plus Playwright, which comes in as a dependency. Nothing to authorize — no account and no API key. The fork publishes no package of its own: the npx line in its README fetches upstream's @mzxrai/mcp-webresearch, which lacks both the CAPTCHA fix and search_scholar. Build it from a clone with pnpm install and pnpm build, then point your client at node and the clone's dist/index.js. Verified on macOS, Linux and Windows. The author describes the code as pre-alpha, so treat it as such.
Build from source — git clone https://github.com/PhialsBasement/mcp-webresearch-stealthified
USE CASES
Search, then open the results worth reading and pull their content.
Visit it directly and extract the content without searching first.
Take the screenshot alongside the extraction so the evidence is kept.
Start broad, narrow as findings come in, and keep every source in the session record.
Search Google Scholar, then compare the papers by authors, venue, year and how often each is cited.
Listed in project code.
search_googlePerforms a web search using Google, ideal for finding current information, news, websites, and general knowledge. Use this tool when you need to research topics, find recent information, or gather data from the web. Returns structured search results with titles, URLs, and snippets.
visit_pageNavigates to a specific URL and extracts the page content in readable format, with option to capture a screenshot. Use this tool to deeply analyze specific web pages, read articles, examine documentation, or verify information directly from the source. Especially useful for in-depth research after identifying relevant pages via search.
take_screenshotCaptures a visual image of the currently loaded webpage. Use this tool when you need to preserve visual information, analyze page layouts, or document the current state of a webpage. Perfect for situations where textual content alone doesn't convey the full context.
search_scholarSearches Google Scholar for academic papers and scholarly articles. Use this tool when researching scientific topics, looking for peer-reviewed research, academic citations, or scholarly literature. Returns structured data including titles, authors, publication details, and citation counts. Ideal for academic research and evidence-based inquiries.
BEFORE YOU INSTALL
4 tools registered in the project's code. The README lists 3; search_scholar is the one it leaves out. Agentic-research is a prompt and takeScreenshot is an argument of visit_page; neither is a tool.
The documented client runs the server on your machine.
CONTEXT COST
4 tool definitions ride along on every turn
INSTALLATION
git clone https://github.com/PhialsBasement/mcp-webresearch-stealthified
cd mcp-webresearch-stealthified
pnpm install
pnpm build{
"mcpServers": {
"webresearch": {
"command": "node",
"args": [
"/path/to/mcp-webresearch-stealthified/dist/index.js"
]
}
}
}Replace /path/to/mcp-webresearch-stealthified with the full path of your clone. The README's own block runs npx @mzxrai/mcp-webresearch@latest, which fetches the upstream package without this fork's CAPTCHA fix or search_scholar.
MCP servers
mzxrai
u14app
DaInfernalCoder
alexcong