"An overview of REST (Representational State Transfer)" matching MCP servers:

Transforms Claude into a persistent intelligence layer with automatic checkpointing, crash recovery, semantic memory, and cross-project learning. It provides 128+ tools for session management, adversarial testing, and browser automation to eliminate state loss and context rebuild costs.

An MCP server that enables AI agents to execute real-world actions through 10 specialized engines covering authenticated API calls, browser automation, visual QA, shell commands, file operations, job scraping, and parallel task execution.

AI-controlled browser farm — run N isolated Chromium instances with 36 MCP tools for device emulation, screenshots, network/geolocation simulation, and diagnostics. Cross-platform: Windows GUI + headed/headless on Linux/macOS.

Enables AI agents to extract clean LLM-ready markdown and readable articles from web pages, parse metadata, tables, links, feeds, and contact info, audit paywalls, SEO, and XSS, and access these tools via Streamable HTTP or a stdio bridge.

MyChart MCP Server

Automates Spectrum/Charter ISP account management tasks such as viewing account overview, paying bills, checking outages, and scheduling technician visits via browser automation.

Enables AI agents to run live Google searches and retrieve organic results, snippets, sitelinks, People Also Ask, related searches, and Google's AI Overview with citations via a zero-dependency MCP server.

MCP server for AT&T telecom account management, automating att.com with Playwright to enable account overview, usage details, bill payment, bill history, and upgrade eligibility checks.

MCP server for managing academic LaTeX projects in Overleaf: create projects, transfer files, compile documents, inspect compiler output, and download PDFs.

Enables AI agents to drive a Chromium browser over MCP, reading pages as a numbered list of controls and performing actions like clicking, filling forms, and asserting page state without screenshots or API keys.

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.

Verified control of the whole desktop for agents on Windows and Linux: apps with no API, windows, shell, browser. MCP server + CLI + REST API.

Enables reading and managing WordPress sites via the WP REST API, including posts, pages, media, taxonomies, users, and arbitrary REST endpoints, with optional authenticated write operations.

An MCP server that enables AI agents to control a real Chrome browser with full login state through 37 structured automation tools, connecting via the Playwriter extension without needing a remote debugging port.

MCP server for browser automation that drives Chrome via an extension, preserving login state and offering 45 tools for navigation, interaction, scraping, and screenshots.

Enables an AI companion to browse Taobao, maintain its own wishlist state machine, request approval under enforced budget rules, and hand a human-checkout list to the user, while all carting and payment remain human-controlled. It also returns login QR codes as images when authentication expires.

An MCP server that gives an agent the open web: searches DuckDuckGo via its no-JavaScript front end, scrapes any URL, and filters/re-ranks results to deliver the top few instead of a wall of links.

Provides complete browser automation capabilities for AI agents via 44 tools, including navigation, element interaction, state management, and session recording.

Enables MCP-compatible AI agents to drive an anti-detection Camoufox-based browser for navigation, interaction, search, extraction, downloads, and batch workflows. It supports multi-tab state tracking and session persistence through cookie import, saved profiles, and stdio or HTTP transport.

A browser automation MCP server providing 30 tools for navigation, interaction, page information, state checks, tab management, and more, enabling natural language control of browsers via MCP-compatible clients.

Enables AI agents to access individual Firefox tabs in their real logged-in state with time-limited, clearly marked, and revocable sharing. Supports both view-only and full-control modes, including interaction, navigation, and automation of the shared tab.

Enables AI agents to interact with Google NotebookLM through browser automation, supporting notebook management, source addition, question answering, and audio overview generation.

Browser agents get stuck when a task needs a person. easi.run provides isolated Chrome on your own Linux server through MCP or REST: watch live, take over for login or approval, then hand back. Saved profiles retain browser state. Requires Linux/Docker. AGPL-3.0; server and model costs separate. Code/setup: https://github.com/julianosig/easi.run

Enables AI agents to read public web content as clean Markdown, search a private library of previously read documents, and access these tools via MCP, REST API, CLI, and WebMCP.

Enables an MCP host agent to delegate bounded reasoning tasks to an ordinary, user-signed-in ChatGPT Chat session and collect concise, size-capped answers back into the original workflow. Runs locally with a managed headless browser profile or an optional unpacked browser extension, requiring no API key, and tracks job state, retries, and recovery IDs.

Exposes a Kali pentesting sandbox to OpenCode agents, enabling health checks, command execution, browser automation, file transfer, finding capture, and report finalization for authorized security scans without requiring LLM keys for the server.

Exposes the React DevTools and TanStack Query/Router state of a Chrome tab to coding agents as MCP tools, enabling inspection, profiling, and mutation of components, queries, and routes from any MCP client.

Enables coding agents to read and modify the state of web apps (Vue, React, Svelte, Pinia, router) through MCP, acting as headless devtools.

Enables running multiple isolated browser instances in parallel, each with independent state and auth cloning, for concurrent task execution.

Connects MCP-compatible AI agents to an anti-detection browser server, providing 47 tools for navigation, interaction, observation, search, downloads, sessions, and batch workflows. Supports multi-tab state, persistent profiles, cookie import, accessibility snapshots, and stdio or HTTP transports.