"Box" matching MCP servers:

Enables MCP clients such as Claude and Cursor to control an isolated cloud machine with a real browser, shell, filesystem, and web access, so agents can navigate pages, click and type, run commands, manage files, and search or fetch web content.

Enables MCP clients to open websites, capture screenshots at multiple breakpoints, and run automated design audits for issues like overflow, small tap targets, low contrast, missing alt text, tiny text, and clipped content.

Enables LLMs to search public discussion platforms for real-world opinions, with semantic routing and no API keys required.

Enables an agent to observe and operate desktop apps and browsers through an accessibility-tree-first view, with clicking, typing, scrolling, dragging and waiting tools. Screenshot handling, coordinate mapping and fail-closed safety rules (risk confirmation, deny-listed apps, stale-observation refusal) are enforced inside the server.

Enables agents to search and deduplicate UK job vacancies across multiple boards, match them against local CVs, and submit complete applications through an automated browser with persistent logins and application memory.

Full-stack utility API with 337+ tools including AI chat, web scraping, weather, finance, SEO, crypto, colors, readability, DNS, and more — all through a single MCP server. Pay-as-you-go credits, no API keys needed.

Enables users to capture any screen or URL, box the region they mean, attach notes, and deliver that annotated feedback—including cropped images, numbered boxes, and the underlying DOM elements or component names—directly to an AI coding agent over MCP. It also lets agents open the annotator, capture a URL, and wait for or retrieve feedback bundles from earlier sessions.

Connects AI agents to an existing Chromium browser profile through a local background service and extension, exposing browser control over MCP stdio. It lets agents navigate tabs, capture accessibility snapshots and screenshots, click, fill forms, type, scroll, drag, and run raw CDP commands, with multiple browser profiles selectable by ID.

Enables AI agents to control a local Chromium browser via CDP for page snapshots, screenshots, human-like interactions, autonomous crawling, API/GraphQL reconnaissance, authenticated differential testing, and Burp-like intercept, repeater, and intruder workflows with scope enforcement and audit logging.

Enables AI agents to test Telegram bots by driving the official Telegram Web client in a real browser, allowing visual verification of bot responses, inline keyboards, and Mini Apps.

Enables secure browser control and automation through MCP, adding domain validation to tab-specific operations while preserving navigation, content, window, history, bookmark, and request-monitoring tools.

Enables AI agents to generate SEO-optimized CSDN blog drafts, refine them against a writing style guide, run SEO self-checks, and optionally publish them to CSDN's draft box via browser automation with rate limiting and a human review gate. Also supports session-based login management, local draft library operations, and reading article statistics through CSDN's public API.

MCP server that adds DuckDuckGo web search and URL/PDF fetching as live internet tools for IBM Bob, requiring no API keys.

MCP server that enables AI agents to control Windows by clicking, typing, and navigating with a visible cursor overlay, using a layered approach (native UIA, browser CDP, pixel fallback) for reliable interaction.