MCP Server RAG Web Browser

What is MCP Server RAG Web Browser about?

Enables AI agents and large language models to interact with the web in real time. The server runs locally, communicates over standard input/output, and forwards search or fetch requests to Apify's RAG Web Browser Actor, returning cleaned content as Markdown (or other formats).

How to use MCP Server RAG Web Browser?

Install dependencies

git clone https://github.com/apify/mcp-server-rag-web-browser.git
cd mcp-server-rag-web-browser
npm install
npm run build

Configure your MCP client (e.g., Claude Desktop) by adding the following entry to claude_desktop_config.json:

"mcpServers": {
  "rag-web-browser": {
    "command": "npx",
    "args": ["-y", "@apify/mcp-server-rag-web-browser"],
    "env": { "APIFY_TOKEN": "your-apify-api-token" }
  }
}

Restart the client and look for the 🔌 icon to confirm the connection.
Issue commands such as a web search or fetch a single URL through the client’s natural‑language interface.

Key features of MCP Server RAG Web Browser

StdIO communication – simple integration with any MCP‑compatible AI client.
search tool – query Google, scrape top N results, and return cleaned content.
Flexible output – choose between text, markdown, or HTML formats.
Configurable scraping – use either Playwright‑based browser or raw HTTP.
Timeout control – set request timeout per call.
Local execution – no need for remote servers, ensuring fast response times.

Use cases of MCP Server RAG Web Browser

Enabling ChatGPT‑like agents to browse the web for up‑to‑date information.
Research assistants that automatically gather and summarize recent articles.
Customer‑support bots that pull product documentation from live websites.
Content creation tools that fetch reference material on demand.

FAQ from the MCP Server RAG Web Browser

Q: Which environments are supported? A: macOS, Windows, and any platform with Node.js v18+.

Q: Do I need an Apify account? A: Yes, an Apify API token (APIFY_TOKEN) is required to run the RAG Web Browser Actor.

Q: Can I change the scraping method? A: Yes, set scrapingTool to browser-playwright or raw-http when calling the search tool.

Q: How many results can I request? A: Use the maxResults parameter; the default is 1.

Q: How do I debug the server? A: Use the Model Context Protocol Inspector:

export APIFY_TOKEN=your-token
npx @modelcontextprotocol/inspector npx -y @apify/mcp-server-rag-web-browser

MCP Server for the RAG Web Browser Actor 🌐

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 MCP server is deprecated in favor of mcp.apify.com

For the same functionality and much more, please use one of these alternatives:

🚀 Recommended: use mcp.apify.com

The easiest way to get the same web browsing capabilities is to use mcp.apify.com with default settings.

Benefits:

✅ No local setup required
✅ Always up-to-date
✅ Access to 6,000+ Apify Actors (including RAG Web Browser)
✅ OAuth support for easy connection
✅ Dynamic tool discovery

Quick Setup:

Go to https://mcp.apify.com
Authorize the client (Claude, VS Code, etc.)
Copy the generated MCP server configuration (or use OAuth flow if supported)
Start using browsing & other tools immediately

🌐 Alternative: direct RAG Web Browser integration

You can also call the RAG Web Browser Actor directly via its HTTP/SSE interface.

Benefits:

✅ Direct integration without mcp.apify.com
✅ Real-time streaming via Server-Sent Events
✅ Full control over the integration
✅ No additional dependencies

Docs: Actor Documentation

🎯 What does this MCP server do?

This server is specifically designed to provide fast responses to AI agents and LLMs, allowing them to interact with the web and extract information from web pages. It runs locally and communicates with the RAG Web Browser Actor in Standby mode, sending search queries and receiving extracted web content in response.

Web Search: Query Google Search, scrape top N URLs, and return cleaned content as Markdown
Single URL Fetching: Fetch a specific URL and return its content as Markdown
Local MCP Integration: Standard input/output (stdio) communication with AI clients

🧱 Components

Tools

name: search description: Query Google Search OR fetch a direct URL and return cleaned page contents. arguments:
- query (string, required): Search keywords or a full URL. Advanced Google operators supported.
- maxResults (number, optional, default: 1): Max organic results to fetch (ignored when query is a URL).
- scrapingTool (string, optional, default: raw-http): One of browser-playwright | raw-http.
  - raw-http: Fast (no JS execution) – good for static pages.
  - browser-playwright: Handles JS-heavy sites – slower, more robust.
- outputFormats (array of strings, optional, default: [markdown]): One or more of text, markdown, html.
- requestTimeoutSecs (number, optional, default: 40, min 1 max 300): Total server-side AND client wait budget. A local abort is enforced.

🔄 Migration Guide

From Local MCP Server to mcp.apify.com

Before (Deprecated local server):

{
  "mcpServers": {
    "rag-web-browser": {
      "command": "npx",
      "args": ["@apify/mcp-server-rag-web-browser"],
      "env": {
        "APIFY_TOKEN": "your-apify-api-token"
      }
    }
  }
}

After (Recommended Apify server):

{
  "mcpServers": {
    "apify": {
      "command": "npx",
      "args": ["@apify/actors-mcp-server"],
      "env": {
        "APIFY_TOKEN": "your-apify-api-token"
      }
    }
  }
}

Or use the hosted endpoint: https://mcp.apify.com (when your client supports HTTP transport / remote MCP).

MCP clients

Claude Desktop: https://claude.ai/download
Visual Studio Code
Apify Tester MCP Client: https://apify.com/jiri.spilka/tester-mcp-client

🛠️ Development

Prerequisites

Node.js (v18 or higher)
Apify API Token (APIFY_TOKEN)

Clone & install:

git clone https://github.com/apify/mcp-server-rag-web-browser.git
cd mcp-server-rag-web-browser
npm install

Build

npm install
npm run build

Debugging

Since MCP servers operate over standard input/output (stdio), debugging can be challenging. For the best debugging experience, use the MCP Inspector.

You can launch the MCP Inspector via npm with this command:

export APIFY_TOKEN=your-apify-api-token
npx @modelcontextprotocol/inspector node dist/index.js

Upon launching, the Inspector will display a URL that you can access in your browser to begin debugging.

📖 Learn more

This repository is maintained for archival purposes only. Please use the recommended alternatives above for active development.