An MCP server that gives AI assistants DuckDuckGo web search plus webpage content fetching and parsing.
pinkpixel-dev/web-scout-mcp
An MCP server that gives AI assistants web search via DuckDuckGo and readable text extraction from one or more URLs.
- Stars
- 151
- Forks
- 20
- Open issues
- 0
- Last commit
- 5 days ago
What is it?
Web Scout MCP is a Model Context Protocol server written in JavaScript. It exposes two tools to MCP-compatible clients such as Claude Desktop and Cursor: DuckDuckGoWebSearch, which runs a query and returns titles, URLs and snippets, and UrlContentExtractor, which fetches pages and strips scripts, styles and navigation to leave readable text.
The extractor accepts either a single URL or an array of URLs and processes them in parallel. The project also includes memory management to avoid crashes on large batches and request throttling to reduce the chance of search requests being blocked. It can be installed globally or locally from npm, or through Smithery, and runs on Node.js 18 or later.
Key features
- 01Searches the web through DuckDuckGo with a configurable result limit
- 02Extracts clean, readable text from web pages by removing scripts, styles and navigation
- 03Processes multiple URLs in parallel
- 04Includes memory management and request rate limiting
- 05Runs over stdio and can be embedded by calling createServer() directly
Use cases
- Giving an AI assistant in Claude Desktop or Cursor the ability to look up current information online
- Collecting article text from a list of URLs for summarization or analysis
- Building a research agent that searches first and then reads the top results
Quick start
- 1
Install the package globally from npm
npm install -g @pinkpixel/web-scout-mcp - 2
Run the server from the command line
web-scout-mcp
Things to know
- The README's license badge says MIT, while the license section and metadata say Apache-2.0.
In collections
Topics
FAQ
- What is web-scout-mcp?
- An MCP server that gives AI assistants web search via DuckDuckGo and readable text extraction from one or more URLs. Web Scout MCP is a Model Context Protocol server written in JavaScript. It exposes two tools to MCP-compatible clients such as Claude Desktop and Cursor: DuckDuckGoWebSearch, which runs a query and returns titles, URLs and snippets, and UrlContentExtractor, which fetches pages and strips scripts, styles and navigation to leave readable text.
- Is web-scout-mcp free to use? What license does it have?
- web-scout-mcp is open source under the Apache-2.0 license. Check the license terms before using it in commercial products.
- Is web-scout-mcp still maintained?
- Actively maintained. The last commit to web-scout-mcp was on Nov 1, 2026.
- What can I use web-scout-mcp for?
- Giving an AI assistant in Claude Desktop or Cursor the ability to look up current information online Collecting article text from a list of URLs for summarization or analysis Building a research agent that searches first and then reads the top results
- How do I install web-scout-mcp?
- Install the package globally from npm: npm install -g @pinkpixel/web-scout-mcp Run the server from the command line: web-scout-mcp
- Where can I get web-scout-mcp?
- The source code and installation instructions are on GitHub: https://github.com/pinkpixel-dev/web-scout-mcp
Summary generated by AI from the project's README. GitHub stats refresh daily.
Related projects
A Go MCP server giving LLM clients web search, image search and page-to-Markdown scraping, with no API keys needed.
Open-source web data platform that turns websites into structured APIs for scraping, crawling, search, monitoring and AI extraction.
Official MCP server that gives AI agents and MCP clients web search, scraping, crawling, browser interaction and Markdown or structured-data extraction via Firecrawl.
Universal content reader MCP server that gives AI agents structured, evidence-graded text from X, YouTube, podcasts, WeChat, and other URLs.
A skill package that gives AI agents real-time web search, vertical domain search, batch search, and full-page content extraction through a CLI.