"Using Python REPL from an MCP server on Windows" matching MCP servers:

Provides LLM agents with a persistent, scriptable browser using Stagehand and Playwright, exposing a single stagehand_eval tool for running JavaScript snippets and AI-driven browser automation.

Provides a local MCP server for AI-powered web crawling on Windows, enabling agents to directly crawl and extract web content without requiring WSL.

An MCP server for fetching and transforming web content into various formats.

This server enables users to download entire websites and their assets for offline access, supporting configurable depth and concurrency settings.

An MCP server that provides browser automation with anti-detect fingerprinting, accessibility snapshots, and ref-based element targeting, powered by Camoufox.

Enables LLMs to automate browser tasks (navigation, clicks, text input) via Selenium through the Model Context Protocol.

A Model Context Protocol server that wraps RPA-Python to enable AI models to directly control browsers for web automation, supporting 54 tools for navigation, interaction, and data extraction.

Enables browser automation and web scraping through Playwright, supporting navigation, screenshots, element interaction, form filling, JavaScript execution, and content extraction.

An MCP server for safe web crawling and scraping of public and authenticated sites using Playwright and Crawlee. It provides tools for scraping single pages, crawling entire sites, validating sessions, and listing supported sites, with built-in security protections and adapter-based extensibility.

Enables users to retrieve Israeli weather forecasts through browser automation, using Playwright to navigate a live weather site and provide page content to the LLM.

Extracts and stores documentation content from Microsoft Learn and GitHub URLs into PocketBase with full-text search, metadata preservation, and automatic collection management for easy retrieval and organization.

Tavily MCP Server implementation that uses fastmcp and supports both sse and stdio transports. It also supports more up to date functionalities of Tavily.

A Python implementation of an MCP server that extracts webpage content, removes ads and non-essential elements, and transforms it into clean, LLM-optimized Markdown.

Enables MCP hosts to search and retrieve job postings from realjobsfromanywhere.com via keyword, location, remote-only, and date filters, plus fetching full details for an individual listing by URL. It provides read-only access with polite rate limiting when the board offers no official seeker API, feed, or MCP.

Converts files (PDF, images, audio, DOCX, XLSX, PPTX) and web content (YouTube transcripts, Bing search, general pages) to Markdown via the Model Context Protocol.

Enables AI agents to query public China Railway 12306 information via MCP, including station lookup, ticket availability, transfer planning, and train route details. It does not support login, booking, or payment.

AI-native web scraper: scrape, crawl and map any site to clean markdown over stdio. MIT-licensed.

Enables AI clients to search live documentation for popular developer libraries and return clean, source-cited summaries via a RAG pipeline.

Enables browser automation with anti-detection features, including navigation, interaction, form filling, and session management.

Enables retrieval and cleaning of official documentation content for popular AI/Python libraries (uv, langchain, openai, llama-index) through web scraping and LLM-powered content extraction. Uses Serper API for search and Groq API to clean HTML into readable text with source attribution.