"File system requirements: mounted directory, persistent state, and full R/W access" matching MCP servers:

Local MCP server that enables downloading papers from arXiv, OpenReview, INFORMS, and Wiley by reusing your Chrome login state.

Provides 18 tools for MacCMS spider development, including website analysis, source code generation, selector debugging, and file operations.

Enables Claude Desktop to download files from web URLs with automatic browser fallback for JavaScript-heavy sites. Supports smart redirect handling, custom file naming, and cross-platform compatibility.

Enables a chat session's owner to reach any host through arbitrary HTTP methods with custom headers and bodies, raw TCP sockets, outbound WebSockets, and browser-grade scraping that solves challenges and discloses explicit failover routing.

Gives AI agents live research and image generation capabilities by automating a logged-in Perplexity Pro browser session.

Provides web access tools (fetch, search, sitemap crawl) through String AI's API, automatically handling anti-bot bypass, CAPTCHA, and JavaScript rendering.

Open-source Chrome extension + MCP server that lets AI agents drive your real, signed-in Chrome by reading the live DOM (no screenshots).

Enables AI assistants and terminals to control a user's already logged-in Chrome session, allowing them to navigate pages, read content, click and type, run JavaScript, and inspect console or network activity.

This MCP server enables browser automation (navigation, clicking, screenshots) and file reading (Excel, Word, PowerPoint, CSV, images) for Claude Code and any MCP client.

Classifies company sites as B2B or B2C and as SaaS, online store, agency, manufacturer, wholesaler, distributor, or marketplace, while matching your own buyer phrases and returning the quoted text and page as evidence. Runs deterministically on Apify, giving one row per domain with grace-free status rows for unreachable, blocked, or empty sites.

Give it a product and a country and it searches Google for manufacturers, wholesalers, and distributors, reads each candidate company's own website, and returns only the ones whose pages back up the claim, with quoted evidence, the domain, and a confidence score. Directories, marketplaces, and social networks are filtered out, and a free summary row reports how many sites were found and checked when nothing qualifies.

Enables crawling sites from start URLs and retrieving internal and external links, file download links, HTML tables as rows, and lists, with controls for crawl depth, page limits, sitemaps, robots.txt, and proxy mode.

Enables watching competitor Shopify, WooCommerce, and SaaS pricing and changelog pages, returning only what changed since the last run as price, stock, product, plan, and changelog diffs. Runs on Apify with per-event pricing and saved state keys for separate baselines.

A fault-tolerant, stealth-enabled Model Context Protocol (MCP) server for web searching and content fetching. Built for AI Agents (Cursor, Claude Code, OpenCode), it uses a stealth browser engine to fetch pages, dynamically handles SPAs/React, and converts bloat into token-optimized Markdown.

Enables web search via Serper API with advanced search operators and webpage scraping capabilities to extract content in plain text or markdown format.

Maps Electron app IPC handlers to MCP tools and provides 33 built-in CDP tools for DOM automation, screenshots, interaction, and debugging, enabling Claude Code to directly control your Electron app.

Provides web search and page fetching capabilities using Ollama's API.

Lets an MCP client list and read pages a user has explicitly shared from a running Firefox session, including visible job listings and recruiter conversations, and search for text within those pages. Access is read-only, granted per page for 30 minutes from the toolbar, and ends on navigation, reload, tab closure, revocation, or client disconnect.

MCP server for responsive web app preview and inspection. It allows previewing URLs on multiple device profiles, capturing screenshots, recording walkthroughs, and inspecting local pages with MCP clients.

Enables AI coding assistants to debug and analyze JavaScript in web pages by managing scripts, breakpoints, network and WebSocket traffic, browser state, and local file inputs/outputs for continuous reverse-engineering workflows.

MyChart MCP Server

Enables reading Slack channels, messages, and threads using the web interface via a persistent browser session, designed for guest users without API access. Does not send messages.

Enables AI agents to manage multiple Google accounts with persistent sessions and anti-detect browser fingerprints, supporting sign-in, account switching, Gmail access, and interaction with any Google SSO website.

Lets any MCP agent control your signed-in Chrome with full login state, offering normal browser tools and an optional Fast JEV mode for bounded-speed typed decisions on the same profile.

Headed Playwright browser MCP server with persistent profile, providing 23 tools for full browser automation while masking PII data.

Enables MCP clients to open and close applications, files, and folders on a Windows machine, manage running apps and File Explorer windows, control Chrome tabs, and perform system actions like shutdown and restart.

Provides access to Jina AI's web tools including URL-to-markdown conversion, web/image/academic search, screenshot capture, document reranking, and semantic deduplication. Works with optional API key for enhanced rate limits and full feature access.

Enables searching YC Work at a Startup jobs, reading job and company details, inspecting application requirements, and submitting applications with dry-run safety while tracking weekly quotas and login status.

Enables coding agents to open the same web page across persistent mobile, tablet, and desktop viewports, interact with it, capture screenshots, inspect the accessible DOM, and run responsive layout audits without losing state between calls.

A token-efficient MCP server that gives AI agents structured access to the web, returning compact page summaries and targeted queries instead of full accessibility dumps.