"browser use" matching MCP servers:

Enables any MCP-compatible AI, whether in the browser or running locally, to create and edit projects, run terminal commands and long-running jobs, and optionally use Docker, all guarded by a policy engine, workspace jail, authentication, and audit logging.

Saves the image currently on the system clipboard to a file (PNG or JPG), enabling AI agents that cannot access the clipboard to use clipboard images.

Publishes an OAuth-gated MCP endpoint with 38 governed tools that let web-based AI clients read and edit local files, run whitelisted shell commands, search code, use read-only Git and SQLite, drive browser and DevTools automation, manage background tasks, ports, clipboard, and localhost services. It keeps that broad control safe by default through a strict command whitelist and configurable allowed folders instead of unrestricted shell access.

Enables AI agents to use Mint as a safety layer for file operations on macOS, providing storage growth analysis, cleanup suggestions, and journaled, reversible deletions via MCP tools.

MCP server to drive browser-migrate operations from Claude, enabling exporting, importing, and migrating browser profiles (bookmarks, history, tabs) between browsers.

Converts PDF files to text for use with MCP-compatible applications like Cursor IDE.

Enables Large Language Models to safely browse and interact with local file systems through secure directory listing, file reading, and content search capabilities. Built with comprehensive security controls and high-performance handling of large directories and files.

Enables filling any PDF form, including scanned or AcroForm, through a browser-based drag-and-drop editor. Works entirely locally with no data leaving the machine.

Local MCP server enabling Codex and ChatGPT to read/write files, execute commands, manage processes, use Git, and inspect images on the user's machine with full privileges.

Node.js server implementing Model Context Protocol (MCP) for filesystem operations, enabling read/write files, directory management, search, and metadata retrieval via SSE transport.

Enables ChatGPT to use a reviewed set of local tools backed by the local Codex environment for project inspection, file edits, commands, browser control, and Excel workbook operations. It also allows explicit Codex model calls only when a task genuinely needs them.

Exposes a governed suite of 38 OAuth-gated tools over one MCP endpoint, letting web-based AI chat clients read and edit files, run whitelisted shell commands, search, and use Git, SQLite, browser automation, DevTools, background tasks, ports, clipboard, notifications, and localhost services on the user's own machine. It also allows local IDEs and automation tools to connect directly over localhost for offline, low-latency access.

Enables ChatGPT to use a reviewed set of local project, browser, and Excel tools backed by a local Codex environment, including file inspection/editing, bounded commands, browser control, and workbook operations. It calls the Codex model explicitly only when a task truly requires it.

Enables MCP clients to observe and control the Windows desktop through the UI Automation accessibility tree — no vision model required — by exposing tools for reading windows and interactive elements, clicking, typing, scrolling, shortcuts, PowerShell, screenshots, virtual desktops, web scraping, file operations and persistent memory, including background-window control without stealing focus. An optional agent mode adds a single natural-language task tool that runs the full upstream agent loop when an LLM provider is configured.

Enables ChatGPT web, desktop, and computer use to access and automate a Mac via 228 MCP tools, including local files, Git, processes, macOS native automation, browser control, and durable goal continuation.

Локальный MCP-сервер, который предоставляет LLM собственный независимый Chromium для управления браузером, включая открытие сайтов, чтение страниц, нажатие кнопок, заполнение форм и создание скриншотов.

It enables MCP-compatible AI clients to run local device, filesystem, shell, PowerShell, Git, browser, HTTP, clipboard and application actions on a Windows PC and a paired Android phone, with session-based device routing. Sensitive operations are gated behind configurable one-use approvals and recorded in a local SQLite audit.

Enables ChatGPT to use a reviewed set of local tools backed by the local Codex environment, supporting project inspection, file edits, bounded commands, browser control, and live Excel workbook interaction. It calls the Codex model explicitly only when a task genuinely needs it.

Enables ChatGPT to use local file, Git, terminal, Chrome/Edge, and Excel tools while optionally invoking Codex only when the model is actually needed.

Serves a local dsh workspace as a protected Streamable HTTP MCP endpoint, letting authenticated web AI agents read, search, patch, inspect, and operate the project, with optional shell commands, LSP support, and public tunneling.