"Exploring RAG through defined workspaces" matching MCP servers:

Enables AI agents to search the web with clean page text, crawl websites into Markdown, extract articles and structured data, and monitor Google News and press releases for LLM context and RAG pipelines. It works with MCP clients and uses the user's own Apify API token for pay-per-result data retrieval.

Fetches web content and returns relevant chunks using RAG with semantic chunking, query-based scoring, and LexRank, supporting PDFs and 50+ languages.

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.

Provides AI agents and assistants with advanced web crawling and RAG capabilities, enabling them to scrape websites and perform semantic search over crawled content.

Provides AI agents with complete web search, crawling, and RAG capabilities through a Docker-based solution combining Model Context Protocol, Crawl4AI, SearXNG, and Supabase.

Enables users to get real-time weather information for Israeli cities through MCP tools, using Playwright to scrape live data and provide it to the language model.

Enables users to find real-world items, listings, or opportunities from live web search results shaped by caller-defined JSON Schemas, then verifies every source URL in code and drops anything that cannot be traced to an actually fetched page.

Enables web scraping and structured data extraction via x402-powered USDC payments on Base mainnet, with tools for scraping URLs into markdown, extracting schema-defined JSON, and checking wallet balances.

MCP server providing tools for web scraping, browser automation, computer vision, audio transcription, and RAG via API.

Enables automation of browser tasks using Playwright by interacting via Claude Desktop for executing user-defined prompts and operations.

MCP server for managing Chrome tabs and tasks, enabling AI agents to search, recall, and organize browser sessions by preventing duplicate tabs, fuzzy searching, and saving workspaces as tasks.

A multi-function Streamable HTTP MCP tool aggregation server that provides web search via Brave, Exa, and SearXNG with multi-key rotation and cross-provider fallback, and supports extensible tool families (URL fetch, code search, RAG) through a pluggable architecture.

Enables AI agents to navigate and operate websites through MCP tools compiled from source-defined routes, with governance controls such as permissions and rate limits.

MCP server wrapping the cmux CLI to let agents control terminal panes, workspaces, input, and browser.

webnav is an MCP server that gives web-browsing AI agents a reusable, deterministic site map, so they stop re-exploring sites every run. It enables page-to-page navigation with zero LLM overhead, pausing only at genuine decision points.

Enables local MCP clients to inspect and interact with Chromium pages, manage isolated workspaces, hand off live tabs, and use scoped account and file grants under explicit human-approved permissions.

Drop-in replacement for Playwright MCP that adds WebMCP support, exposing page-defined tools as gated webmcp:* tools with provenance tracking, schema-change warnings, and mandatory confirmation.

Enables automated end-to-end testing powered by Playwright where test cases are defined in natural language and executed by AI. Uses lightweight snapshot analysis with vision mode fallback for sophisticated testing scenarios.

Enables secure remote development on Windows by allowing LLM clients to manage files, run commands, and automate browsers within sandboxed workspaces, with multi-project switching and OAuth authentication.

High-speed Google search intelligence and token-optimized Markdown grounding engine for AI LLMs, autonomous agents, and RAG pipelines.