RAG Web Browser MCP Server

What does “RAG Web Browser” MCP Server do?

The RAG Web Browser MCP Server is a specialized tool designed to provide AI assistants and large language models (LLMs) with the ability to interact with the web and extract up-to-date information from web pages. Operating locally, it connects to the RAG Web Browser Actor in Standby mode, facilitating seamless communication between AI agents and web content. The main functions include performing web searches, scraping the top N URLs from search results, and returning their cleaned content as Markdown. Additionally, it can fetch the content of a single URL and present it in a user-friendly markdown format. This enables LLMs to access, summarize, and utilize live web data, enhancing their capabilities for research, content generation, and workflow automation.

List of Prompts

No prompt templates are explicitly mentioned in the repository or documentation.

Ready to grow your business?

Start your free trial today and see results within days.

Request demo Log in

List of Resources

No explicit resources are defined in the available documentation or repository files.

List of Tools

• search:
  Query Google Search, scrape the top N URLs from the results, and return their cleaned content as Markdown.
  • Arguments:
    • query (string, required): Search term or URL
    • maxResults (number, optional): Maximum number of search results to scrape (default: 1)
    • scrapingTool (string, optional): Select a scraping tool (‘browser-playwright’ or ‘raw-http’; default: ‘raw-http’)
    • outputFormats (array, optional): Output formats (’text’, ‘markdown’, ‘html’; default: [‘markdown’])
    • requestTimeoutSecs (number, optional): Max time in seconds for the request (default: 40)

Join our newsletter

Get latest tips, trends, and deals for free.

Email address

Subscribe

Use Cases of this MCP Server

• Automated Web Searching
  Enable AI agents to conduct live web searches and retrieve summarized information from the top results, useful for research and answering up-to-date queries.

• Content Extraction for RAG Pipelines
  Integrate with Retrieval-Augmented Generation (RAG) workflows to fetch and process web content as reliable context for LLM responses.

• Summarization of Web Pages
  Fetch and clean the content of specific URLs, allowing developers or LLMs to quickly ingest and summarize relevant information.

• Data Collection for Market/Competitive Analysis
  Use the server to scrape competitor sites or market news, providing real-time intelligence for business applications.

How to set it up

Windsurf

1. Ensure Node.js and npm are installed.
2. Locate your Windsurf configuration file.
3. Add the RAG Web Browser MCP Server to the mcpServers object:

   {
     "mcpServers": {
       "rag-web-browser": {
         "command": "npx",
         "args": ["@apify/mcp-server-rag-web-browser@latest"]
       }
     }
   }
   

4. Save the configuration and restart Windsurf.
5. Verify the server is running and accessible.

Securing API Keys (Example)

{
  "mcpServers": {
    "rag-web-browser": {
      "command": "npx",
      "args": ["@apify/mcp-server-rag-web-browser@latest"],
      "env": {
        "APIFY_TOKEN": "process.env.APIFY_TOKEN"
      },
      "inputs": {
        "apiKey": "${APIFY_TOKEN}"
      }
    }
  }
}

Claude

1. Confirm Node.js and npm availability.
2. Open Claude’s configuration file.
3. Add the MCP server as follows:

   {
     "mcpServers": {
       "rag-web-browser": {
         "command": "npx",
         "args": ["@apify/mcp-server-rag-web-browser@latest"]
       }
     }
   }
   

4. Save and restart Claude.
5. Check for correct integration.

Cursor

1. Install Node.js and npm if needed.
2. Find Cursor’s config file.
3. Insert the MCP Server:

   {
     "mcpServers": {
       "rag-web-browser": {
         "command": "npx",
         "args": ["@apify/mcp-server-rag-web-browser@latest"]
       }
     }
   }
   

4. Save config, restart Cursor.
5. Confirm server appears in MCP tools.

Cline

1. Make sure Node.js and npm are installed.
2. Edit Cline’s configuration.
3. Add the following JSON:

   {
     "mcpServers": {
       "rag-web-browser": {
         "command": "npx",
         "args": ["@apify/mcp-server-rag-web-browser@latest"]
       }
     }
   }
   

4. Save and restart Cline.
5. Validate the MCP server connection.

Note: Secure your API keys using environment variables as shown in the Windsurf example.

How to use this MCP inside flows

Using MCP in FlowHunt

To integrate MCP servers into your FlowHunt workflow, start by adding the MCP component to your flow and connecting it to your AI agent:

Click on the MCP component to open the configuration panel. In the system MCP configuration section, insert your MCP server details using this JSON format:

{
  "rag-web-browser": {
    "transport": "streamable_http",
    "url": "https://yourmcpserver.example/pathtothemcp/url"
  }
}

Once configured, the AI agent is now able to use this MCP as a tool with access to all its functions and capabilities. Remember to change “rag-web-browser” to whatever the actual name of your MCP server is and replace the URL with your own MCP server URL.

Overview

Based on the tables below, the RAG Web Browser MCP Server is streamlined and highly targeted for web interaction tasks but lacks broader MCP primitives like prompts and resources. It provides all essentials for setup and secure operation, with a strong, well-documented primary tool. Sampling and Roots support are not mentioned.

Our opinion

The MCP server is focused and functional, ideal for scenarios needing web data access inside LLM workflows. It’s easy to set up, has a clear license, and is moderately popular. The absence of prompt templates and explicit resources limits its flexibility for more customized or complex use cases, but for RAG and live web search, it excels. Score: 7/10

MCP Score