📌Overview

Purpose: To facilitate real-time web research for the Claude AI by integrating a Model Context Protocol (MCP) server that captures and processes web content.

Overview: The MCP Web Research Server enables users to conduct in-depth research by seamlessly incorporating online information into the Claude AI system. It enhances the AI's capabilities by allowing it to extract content from the web and manage research sessions effectively.

Key Features:

• Google search integration: Enables the AI to perform searches and retrieve relevant web results in real-time for better-informed responses.

• Webpage content extraction: Allows the AI to visit specific URLs and extract content from those pages, enriching the data available for analysis and responses.

• Research session tracking: Maintains a log of visited pages, search queries, and captured content, helping users keep track of their research activities.

• Screenshot capture: Provides the ability to take and store screenshots of webpages, facilitating easy reference and citation of sources during research.

---

MCP Web Research Server

A Model Context Protocol (MCP) server for web research. Enhance your research capabilities by bringing in real-time information.

Features

• Google search integration
• Webpage content extraction
• Research session tracking (visited pages, search queries, etc.)
• Screenshot capture

Prerequisites

• Node.js >= 18 (includes npm and npx)
• Claude Desktop app

Installation

1. Install the Claude Desktop app and ensure npm is installed.

2. Add the following entry to your claude_desktop_config.json:

   {
     "mcpServers": {
       "webresearch": {
         "command": "npx",
         "args": ["-y", "@mzxrai/mcp-webresearch@latest"]
       }
     }
   }
   

This configuration allows Claude Desktop to start the web research MCP server automatically.

Usage

Start a chat with Claude and send prompts that could benefit from web research. For enhanced research, use the agentic-research prompt available in Claude Desktop.

Tools

1. search_google

   • Performs Google searches and extracts results.
   • Arguments: { query: string }

2. visit_page

   • Visits a webpage and extracts its content.
   • Arguments: { url: string, takeScreenshot?: boolean }

3. take_screenshot

   • Takes a screenshot of the current page.

Prompts

agentic-research

A guided research prompt that helps Claude conduct thorough web research. It instructs Claude to:

• Start with broad searches to understand the topic.
• Prioritize high-quality, authoritative sources.
• Iteratively refine research based on findings.
• Keep you informed and allow interactive guidance.
• Cite sources with URLs.

Resources

• Captured webpage screenshots can be accessed in Claude Desktop.
• The research session maintains:
  • Search queries
  • Visited pages
  • Extracted content
  • Screenshots
  • Timestamps

Suggestions

To enhance research results without using the agentic-research prompt, consider suggesting high-quality sources (e.g., "news today from Reuters or AP").

Problems

This is pre-alpha code and may contain bugs. Check Claude Desktop's MCP logs for issues:

tail -n 20 -f ~/Library/Logs/Claude/mcp*.log

Development

To set up the development environment:

# Install dependencies
pnpm install

# Build the project
pnpm build

# Watch for changes
pnpm watch

# Run in development mode
pnpm dev

Requirements

• Node.js >= 18
• Playwright (automatically installed)

Verified Platforms

• macOS
• Linux (not yet verified)

License

MIT

Author

mzxrai