Install
mcp-registry/mcp-webresearch
mcp-webresearch logo

mcp-webresearch

Author: mzxrai

Description: MCP web research server (gives Claude real-time web research with Google search, page extraction, screenshots and session tracking)

Stars: 271

Forks: 60

License: MIT License

Category: Open Source

Overview

Installation

1. Clone the repository
git clone https://github.com/mzxrai/mcp-webresearch.git cd mcp-webresearch
2. Install dependencies (Node ≥18 is recommended)
npm install
3. Provide any required environment variables in a .env file or your shell (values below are examples)
# API key for your preferred search backend SERPAPI_API_KEY="xxxxxxxxxxxxxxxx" # If the tool is chained with other MCP tools you might also export ANTHROPIC_API_KEY="claude-xxxxxxxxxxxxxxxx"
4. Run the server locally
npm start # default port 3000 # or specify a custom port PORT=8080 npm start
5. Docker (optional)
docker build -t mcp-webresearch . docker run -e SERPAPI_API_KEY=xxxxxxxxxxxxxxxx -p 3000:3000 mcp-webresearch

01

search_google

Performs Google searches and extracts results

02

visit_page

Visits a webpage and extracts its content

03

take_screenshot

Takes a screenshot of the current page

License: MIT License
Updated 7/30/2025