RAG Web Browser
Implementation of an MCP server for the RAG Web Browser Actor. This Actor serves as a web browser for large language models (LLMs) and RAG pipelines, similar to a web search in ChatGPT.
What is RAG Web Browser?
RAG Web Browser is a Model Context Protocol (MCP) server that allows AI assistants like Claude, Cursor, and VS Code to implementation of an mcp server for the rag web browser actor. this actor serves as a web browser for large language models (llms) and rag pipelines, similar to a web search in chatgpt.
Implementation of an MCP server for the RAG Web Browser Actor. This Actor serves as a web browser for large language models (LLMs) and RAG pipelines, similar to a web search in ChatGPT.
This server falls under the Browser Automation and Search & Data Extraction categories on MCPgee, the world's largest MCP server directory with 33,000+ servers.
Features
- Implementation of an MCP server for the RAG Web Browser Acto
Use Cases
Maintainer
Works with
Installation
Manual Installation
npx rag-web-browserConfiguration
Configuration Details
claude_desktop_config.json
Performance
Response Metrics
Resource Usage
How to Set Up and Use RAG Web Browser
The RAG Web Browser MCP server gives AI assistants the ability to search Google and fetch live web pages, returning clean Markdown, text, or HTML content suitable for RAG pipelines. It is built on the Apify platform, which handles browser rendering and JavaScript-heavy pages via Playwright, and works like the web-search capability in ChatGPT — letting language models answer questions with up-to-date information. Developers building LLM applications use it to inject fresh web content into their model's context without managing a headless browser themselves.
Prerequisites
- An Apify account with a valid API token (free tier available)
- Node.js 18 or higher (for local setup)
- An MCP-compatible client such as Claude Desktop or Claude Code CLI
- Internet access from the machine running the MCP client
Get your Apify API token
Sign up at apify.com and navigate to Settings > Integrations to copy your personal API token. This is the only credential the server needs.
Add the server to Claude Desktop
The easiest setup uses npx to run the server on demand. Add the block below to your claude_desktop_config.json and paste in your Apify token.
Optional: build from source
If you want to run the server locally from source code rather than via npx, clone the repo and build it with npm.
git clone https://github.com/apify/mcp-server-rag-web-browser.git
cd mcp-server-rag-web-browser
npm install
npm run build
node dist/index.jsTest the search tool
Once configured, ask Claude to search for something to confirm the server is working. The 'search' tool accepts a query string or a direct URL.
Tune output format and scraping mode
The search tool supports outputFormats (markdown, text, or html) and scrapingTool (raw-http for speed or browser-playwright for JavaScript-heavy pages). Specify these in your prompt or via tool parameters.
RAG Web Browser Examples
Client configuration
Claude Desktop configuration for the RAG Web Browser MCP server using npx.
{
"mcpServers": {
"rag-web-browser": {
"command": "npx",
"args": ["@apify/mcp-server-rag-web-browser"],
"env": {
"APIFY_TOKEN": "your-apify-api-token"
}
}
}
}Prompts to try
Example prompts that use the RAG Web Browser's search and page-fetch capabilities.
- "Search the web for the latest Node.js LTS release notes and summarize the changes"
- "Fetch the content from https://docs.anthropic.com and tell me what models are available"
- "Look up the current price of AAPL stock and format it as a table"
- "Search for 'best practices for RAG pipelines 2025' and give me the top 5 recommendations"
- "Fetch this URL using a real browser to get the JavaScript-rendered content: https://example.com/app"Troubleshooting RAG Web Browser
API call fails with 'Unauthorized' or 'Invalid token'
Double-check that APIFY_TOKEN is set to your personal API token from the Apify console under Settings > Integrations. Tokens start with 'apify_api_' — ensure you are not using an Actor run token by mistake.
JavaScript-rendered page content is missing or incomplete
Pass scrapingTool: 'browser-playwright' in the tool parameters. The default 'raw-http' mode fetches static HTML only and skips client-side rendering.
Search returns stale or unexpected results
The server queries Google Search via Apify's RAG Web Browser Actor. If results are stale, increase maxResults or refine your query string with Google search operators like 'site:' or 'after:' for date filtering.
Frequently Asked Questions about RAG Web Browser
What is RAG Web Browser?
RAG Web Browser is a Model Context Protocol (MCP) server that implementation of an mcp server for the rag web browser actor. this actor serves as a web browser for large language models (llms) and rag pipelines, similar to a web search in chatgpt. It connects AI assistants to external tools and data sources through a standardized interface.
How do I install RAG Web Browser?
Follow the installation instructions on the RAG Web Browser GitHub repository. Clone the repo, install dependencies, and add the server config to your AI client.
Which AI clients work with RAG Web Browser?
RAG Web Browser works with all major MCP-compatible AI clients including Claude Desktop, Claude Code, Cursor, VS Code (GitHub Copilot), Windsurf, and Cline.
Is RAG Web Browser free to use?
Yes, RAG Web Browser is open source and available under the Apache 2.0 license. You can use it freely in both personal and commercial projects.
RAG Web Browser Alternatives — Similar Browser Automation Servers
Looking for alternatives to RAG Web Browser? Here are other popular browser automation servers you can use with Claude, Cursor, and VS Code.
Chrome DevTools MCP
★ 40.6kAI-powered Chrome automation server with natural language element detection. Control Chrome browser through MCP protocol for testing, debugging, and performance analysis. Features 91% accuracy in element location, works with free AI models, and suppo
UI TARS Desktop
★ 34.9k📇 🏠 - Browser automation capabilities using Puppeteer, both support local and remote browser connection.
Playwright
★ 32.8kA production-ready browser automation server that enables AI assistants to interact with web pages using tools for navigation, element interaction, and data extraction. It features a built-in Inspector UI and robust crash recovery for reliable automa
Page Agent
★ 18.0kJavaScript in-page GUI agent. Control web interfaces with natural language.
Chrome
★ 11.7kAn extension-based MCP server that enables AI assistants to control your browser, leveraging existing sessions and login states for automation and content analysis. It provides over 20 tools for semantic tab search, interactive element manipulation,
LAMDA
★ 7.8kThe most powerful Android RPA agent framework, next generation mobile automation.
Browse More Browser Automation MCP Servers
Explore all browser automation servers available in the MCPgee directory. Each server includes setup guides for Claude, Cursor, and VS Code.
Set Up RAG Web Browser in Your Editor
Choose your AI client for step-by-step setup instructions.
Quick Config Preview
Add this to your claude_desktop_config.json or .cursor/mcp.json
Ready to use RAG Web Browser?
Browse our complete directory of 33,000+ MCP servers, read setup guides for your editor, and start building with the Model Context Protocol.