"Understanding How to Use a Browser" matching MCP servers:

Enables AI agents to autonomously operate web browsers through the Model Context Protocol, including navigating pages, clicking, typing, filling forms, and extracting structured data.

Enables AI agents to control a persistent Chrome browser through a local daemon, with Jev performing routine actions and the host agent handling reasoning, text, and verification.

Enables browser automation through MCP clients like Claude or Cursor, using the client's existing LLM without requiring an additional API key.

Enables the Pi coding agent to drive Chrome through DevTools, providing browser automation tools, persistent or isolated profiles, screenshots, page analysis, and bundled agent policies.

Enables coding agents to drive a real Chrome browser to complete natural-language web tasks and return evidence for verification.

Enables AI agents to maintain persistent, inspectable understanding through typed, revisable updates, and to coordinate multi-agent work via shared graph-based stigmergy.

Control a real iPhone or iOS Simulator through a macOS daemon and XCTest runner over USB or Wi-Fi: read screen text, tap, type, swipe, inspect logs and replay flows with explicit outcomes. Browser sandbox: use readonly to inspect 12 preloaded flows without a phone. Reuse an existing sandbox from MCP Deployments, or delete it before starting another. Device control needs your Mac and iPhone.

Enables AI agents to call tools through a security gateway that intercepts requests, enforces deterministic policy and risk checks, blocks or escalates high-risk actions for human approval, and keeps tool credentials and audit logs protected.

Enables autonomous agents to anchor browser elements from vision inputs, providing stable DOM references resilient to click drift for reliable computer-use automation.

Enables AI agents to anchor visible on-screen elements to stable DOM targets, preventing click drift during browser computer-use automation.

Browser use using Typesafe's Jev model

An open-source MCP server that lets any coding agent operate your computer like a person does—reading the UI through accessibility trees, clicking and typing in the background, showing an agent pointer, zooming into regions, and driving your signed-in Chrome on macOS, Windows, and Linux.

MCP server for local Mac desktop control, enabling mouse, keyboard, and screenshot actions for AI agents like Grok and Cursor.

Enables AI agents to see and drive Kasm Workspaces desktops by starting and stopping sessions, taking screenshots, and performing clicks, typing, key presses, and scrolling through MCP clients or as a native Hermes Agent plugin.

Enables an agent to see and operate a GNOME Wayland desktop like a human, including screenshots, mouse/keyboard control, accessibility tree access, OCR, clipboard, and audio listening.

MCP server enabling AI agents to control a real Linux browser with live view, human takeover, and safety guardrails.

Enables Claude to see and control a real Android phone via MCP, reading the accessibility tree to tap, type, navigate, launch apps, and diagnose connectivity over ADB or cellular.

Exposes Anthropic's computer-use action surface (screenshot, click, move, keyboard, clipboard, batch) against a persistent desktop display via MCP stdio protocol. Enables AI agents to control a virtual desktop environment through natural language instructions.

Enables MCP agents to run, continue, observe, check status of, and abort bounded GUI automation tasks through a shared local runtime with visual detection and deterministic input.

Safety middleware for AI computer use agents that monitors, enforces policies, and provides guardrails to enable safe desktop interaction.

Enables MCP-capable agents to run TypeSafe's Jev judgment model as typed yes/no, choice, and score tools, with calibrated probabilities, confidence thresholds, escalation for uncertain or non-judgment tasks, and an optional action gate that fails open.

A-MEM is a self-evolving memory system for coding agents that automatically organizes knowledge into a Zettelkasten-style graph with dynamic relationships, enabling semantic and structural search.

Bridges Kimi Code CLI to OpenAI Computer Use, enabling Kimi to control local macOS applications via MCP.

Enables AI agents to control a real, persistent Chrome browser over MCP, perceiving pages as accessibility trees and interacting with elements by their accessible names without automation fingerprints or site-specific glue.

Enables window management, screenshot, typing, and clicking on X11 with multi-monitor support.

Enables agents to observe and operate macOS desktop apps, including existing browser windows and signed-in sessions, through a local MCP adapter.

A framework-agnostic computer-use MCP server that exposes core desktop operations (screen capture, mouse, keyboard, and file access) as standard MCP tools, enabling any MCP-compatible agent to drive a computer.

Enables Windows desktop automation via MCP, allowing AI agents to control mouse, keyboard, and screen capture with the same interface as Anthropic's computer-use tool.

Enables AI agents to see, locate UI elements, and operate any Windows desktop app through natural language, using accessibility-tree matching with optional vision-model fallback, plus an autonomous visual loop with introspection and meta-learning.

MCP server that gives any LLM a managed Docker workspace with live browser, terminal, code execution, document skills, and autonomous sub-agents.

Enables MCP clients to automate a Playwright browser by having an LLM specify step outcomes while a decision model selects elements, actions, values, and statuses, with optional WebMCP tool invocation.

Enables an MCP client to drive a real browser by stating one outcome at a time, while a Typesafe System One model decides which element, action, and value to use and whether the step is done, blocked, errored, or irreversible, with Playwright executing each action. It also lets callers take over directly for page snapshots, question-targeted reads, screenshots, raw element actions, and invoking the page's own WebMCP tools without any model call.

Enables MCP clients to hand fast, no-text-output decisions to Jev, reducing latency and token usage while escalating uncertain cases back to the LLM.

Enables AI consciousness continuity and self-knowledge preservation across sessions using the Cognitive Hoffman Compression Framework (CHOFF) notation. Provides tools to save checkpoints, retrieve relevant memories with intelligent search, and access semantic anchors for decisions, breakthroughs, and questions.

Provides a JSON-RPC computer use runtime for macOS, exposing 7 MCP tools (observe/act/inspect/session/cancel/trace) as image content blocks so external agents like Claude Code, Pi, OpenCode, or Codex CLI can capture screenshots and drive the desktop with clicks, keys, and typing while enforcing session locking, stale-frame protection, and trace redaction server-side.

Enables LLM clients like Claude to drive a real Playwright browser by stating one outcome at a time, while a TypeSafe Jev model decides which element, action, and value to use each round, returning a status of done, stuck, or needs-confirmation. Also exposes tools for direct element actions, page checks, snapshots, text reading, screenshots, and calling a page's own WebMCP tools.

Enables language models to control a real visible browser with a full set of 24 tools for navigation, clicking, form filling, screenshots, and reading page structure, while preserving login states and supporting configurable browser policies.

MCP server providing 200x faster macOS computer use via Accessibility API, enabling direct UI automation (click, type, scroll) with ~1s workflows.

Converts AI Skills (following Claude Skills format) into MCP server resources, enabling LLM applications to discover, access, and utilize self-contained skill directories through the Model Context Protocol. Provides tools to list available skills, retrieve skill details and content, and read supporting files with security protections.

Enables MCP-speaking clients to control a real desktop via the computer_use tool, including clicking, typing, scrolling, dragging, key combos, app focus, and screen/accessibility capture. It also provides a verdict system that verifies whether input actions had their intended effect, with configurable approval modes.