apify/mcp-server-rag-web-browser
An MCP server for Apify's RAG Web Browser Actor, performing web searches, scraping URLs, and returning content in Markdown within the MCP protocol.
About this tool
apify/mcp-server-rag-web-browser
Source: GitHub Repository
Description
apify/mcp-server-rag-web-browser is an open-source MCP (Model Context Protocol) server designed for Apify's RAG Web Browser Actor. It enables integration with AI assistants and LLM (Large Language Model) pipelines to perform automated web search, scrape content from URLs, and return cleaned content in Markdown format within the MCP protocol.
Features
- Web Search via MCP: Allows AI assistants (such as Claude Desktop) to perform web searches programmatically, scrape the top N results, and retrieve their cleaned content as Markdown.
- Fetch & Scrape URLs: Supports fetching a single URL and returning its cleaned content as Markdown.
- Search Tool:
searchtool queries Google Search, scrapes the top N URLs from results, and returns cleaned content in Markdown.- Arguments:
query(string, required): Search term or URL.max_results(number, optional): Maximum number of search results to scrape (default: 1).
- Prompt Integration:
- Prompts can trigger search actions and return crawled web pages as text or Markdown.
- MCP Protocol: Implements the Model Context Protocol for secure, controlled interaction with AI agents and external data sources.
- SSE (Server-Sent Events) Support: Can stream responses back to clients using SSE, allowing for real-time updates.
- Local Development & Testing:
- Example clients for stdio and chat interfaces.
- SSE transport example for streaming.
- Debugging support with MCP Inspector.
- Cross-platform: Works on MacOS and Windows.
- Open Source: Licensed under Apache-2.0.
Configuration & Requirements
- Prerequisites:
- MacOS or Windows
- Node.js v18 or higher
- Apify API Token (
APIFY_API_TOKEN) - Claude Desktop or another MCP client
- Setup involves cloning the repository, installing dependencies, building the project, and configuring the MCP client (e.g., Claude Desktop) to connect to the server.
Pricing
No pricing information is provided; this is an open-source project under the Apache-2.0 license.
Tags
mcp, web, scraping, rag, automation
Category
code-execution-automation-mcp-servers
Loading more......
Information
Categories
Tags
Similar Products
6 result(s)MCP servers for automating and controlling the user's browser using existing browser profiles, ideal for tasks requiring logged-in sessions and avoiding bot detection. Includes implementations by browsermcp and modelcontext.
Integrates with web browsers to enable automated web scraping, form filling, and interaction with web applications. This is a popular and well-maintained MCP server focused on browser automation.
Provides an async browser automation server using OpenAI's GPT-4o model, enabling remote web navigation, content extraction, and task execution with configurable browser contexts. This is a robust MCP server solution for browser automation.
An MCP server providing control over Android devices via ADB, including screenshot capture, UI analysis, package management, and command execution.
A secure MCP server for executing shell commands with robust security controls, enabling protected command-line operations. Directly relevant as a widely-used MCP server for secure CLI automation.
An MCP server that integrates with 3D printer management systems (OctoPrint, Klipper, Duet, etc.) enabling remote control, STL file manipulation, slicing, and advanced print job workflows, highlighting MCP servers in IoT and device automation.