# mcp-webresearch

> MCP Server

This repository provides an MCP server for web research, integrating Google search, webpage content extraction, research session tracking, and screenshot capture for use with the Claude Desktop app.

## Overview

- **Category:** Search & Knowledge
- **Language:** JavaScript
- **Stars:** 300
- **Forks:** 37
- **Owner:** mzxrai
- **GitHub:** https://github.com/mzxrai/mcp-webresearch
- **Created:** 2024-12-06T04:28:52+00:00
- **Updated:** 2025-03-27T07:07:24+00:00
- **Source:** https://model-context-protocol.com/servers/mcp-web-research-server-claude-integration

## Setup

## Setup

1.  Ensure you've downloaded and installed the [Claude Desktop app](https://claude.ai/download) and you have npm installed.
2.  Add the following entry to your `claude_desktop_config.json` (on Mac, found at `~/Library/Application\ Support/Claude/claude_desktop_config.json`):

```json
{
  "mcpServers": {
    "webresearch": {
      "command": "npx",
      "args": ["-y", "@mzxrai/mcp-webresearch@latest"]
    }
  }
}
```
This config allows Claude Desktop to automatically start the web research MCP server when needed.

## Tools

## Available Tools

1.  Google search integration (Performs Google searches and extracts results)
2.  Webpage content extraction (Visits a webpage and extracts its content)
3.  Research session tracking (Tracks list of visited pages, search queries, etc.)
4.  Screenshot capture (Takes a screenshot of the current page)
5.  `search_google` (Performs Google searches and extracts results with `{ query: string }` argument)
6.  `visit_page` (Visits a webpage and extracts its content with `{ url: string, takeScreenshot?: boolean }` argument)
7.  `take_screenshot` (Takes a screenshot of the current page with no arguments required)