MCP Web Research Server

A server for web research that brings real-time information into AI models and researches any topic.

A Model Context Protocol (MCP) server for web research.

Bring real-time info into Claude and easily research any topic.

- Google search integration --- THIS FORK FIXES THIS --- NOW NO LONGER GETTING CAPTCHA BLOCKED
- Webpage content extraction
- Research session tracking (list of visited pages, search queries, etc.)
- Screenshot capture

- Node.js>= 18 (includesnpmandnpx)
- Claude Desktop app

First, ensure you've downloaded and installed theClaude Desktop appand you have npm installed.

{ "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.

Simply start a chat with Claude and send a prompt that would benefit from web research. If you'd like a prebuilt prompt customized for deeper web research, you can use theagentic-researchprompt that we provide through this package. Access that prompt in Claude Desktop by clicking the Paperclip icon in the chat input and then selectingChoose an integration→webresearch→agentic-research.

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

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

- Takes a screenshot of the current page
- No arguments required

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

- Start with broad searches to understand the topic landscape
- Prioritize high-quality, authoritative sources
- Iteratively refine the research direction based on findings
- Keep you informed and let you guide the research interactively
- Always cite sources with URLs

We expose two things as MCP resources: (1) captured webpage screenshots, and (2) the research session.

When you take a screenshot, it's saved as an MCP resource. You can access captured screenshots in Claude Desktop via the Paperclip icon.

The server maintains a research session that includes:

- Search queries
- Visited pages
- Extracted content
- Screenshots
- Timestamps

For the best results, if you choose not to use theagentic-researchprompt when doing your research, it may be helpful to suggest high-quality sources for Claude to use when researching general topics. For example, you could promptnews today from reuters or APinstead ofnews today.

This is very much pre-alpha code. And it is also AIGC, so expect bugs.

If you run into issues, it may be helpful to check Claude Desktop's MCP logs:

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

# Install dependencies pnpm install # Build the project pnpm build # Watch for changes pnpm watch # Run in development mode pnpm dev

- Node.js >= 18
- Playwright (automatically installed as a dependency)

Scrape, crawl, and extract data from any website using the Firecrawl API.

Web scraper exposing 5 MCP tools — crawl, markdown extraction, search-and-crawl, sitemap parsing, and LLM JSON-schema structured extraction. AGPL-3.0.

Aggregates trending topics from over 20 sources in real-time, with customizable fields and RSS feed support.

Best people search engine that reduces the time spent on talent discovery.

Job search engine with 500k+ listings across Austria, Germany and Switzerland (alleskralle.com).

Hosted MCP server for the APITube News API: search articles from 500,000+ sources in 60+ languages, filtered by sentiment, entities, topics and source quality.

Live Austin-area MLS listings in your AI assistant — active listings, property details, schools, taxes, and neighborhood data for the Austin metro. Free remote MCP server, no install.

Real-time product search and price comparison across 15+ SG/SEA/US merchants (161M+ products) via MCP server and REST API