Agent Switchboard

Browse Agents

Task

I need to control a desktop computer

Remove task

Agents that see the screen and work the mouse and keyboard on a desktop, the way a person does.

Picked from listings that mention computer use, desktop, mouse or screen in their name, description, tags or skills; those in Browser & Computer Use, or with API or MCP access, rank higher. About this task →

10 official agents fit this task

all Verified · 6 No auth needed · 2 API · 5 MCP · 5 CLI · 1 Extension

UI-TARS Desktop

CLI · API

ByteDance's multimodal GUI agent stack that controls desktop and browser interfaces from natural language using…

VerifiedOfficialby ByteDance · Browser & Computer Use · API Key

Microsoft UFO

CLI

Automates Windows desktop apps through natural-language tasks with the UFO2 Desktop AgentOS, and orchestrates agents…

VerifiedOfficialby Microsoft · Browser & Computer Use, Autonomous Agents · 4 skills · No auth

Claude Cowork

API

Works as an AI coworker in Claude that reads your files, runs scheduled tasks across your apps, and ships finished…

VerifiedOfficialby Anthropic · Autonomous Agents, Browser & Computer Use · 3 skills · OAuth 2.0

Agent TARS

CLI

ByteDance's multimodal AI agent for desktop and browser automation — controls GUIs, browsers, and shell via vision and…

VerifiedOfficialby ByteDance · Browser & Computer Use, Infrastructure & Ops · 4 skills · No auth

Chrome DevTools MCP

MCP

Official Chrome DevTools MCP server. Gives AI coding agents browser debugging — inspect DOM, execute JS, capture…

VerifiedOfficialby Chrome DevTools · Browser & Computer Use · 4 skills · No auth

Firefox DevTools MCP

MCP · CLI

Lets MCP clients automate and debug a local Firefox via WebDriver BiDi: navigate pages, fill forms, inspect network and…

VerifiedOfficialby Mozilla · Browser & Computer Use, Code & DevTools · 4 skills · No auth

ARTEMIS

CLI

Converts natural-language instructions into reliable Android device automation for coding agents, capturing logs and…

VerifiedOfficialby Google · Browser & Computer Use, Code & DevTools · 3 skills · No auth

Figma MCP Server

MCP

Gives coding agents Figma design context, variables, screenshots, and generated code from frames, and lets them write…

VerifiedOfficialby Figma · Code & DevTools, Content & Media · 4 skills · OAuth 2.0

Page Agent

MCP · Extension

Embeds a GUI agent in any web page with one script tag, driving the existing DOM from natural-language instructions…

VerifiedOfficialby Alibaba · Browser & Computer Use, Code & DevTools · 5 skills · API Key

Safari MCP Server

MCP

Connects AI agents to a live Safari window for web debugging: DOM inspection, network monitoring, console logs…

VerifiedOfficialby Apple · Browser & Computer Use, Code & DevTools · 3 skills · No auth
/browse
10 agents fit the task · task: control-a-computer · official
verified: 10 · no-auth: 6 · api: 2 · mcp: 5 · cli: 5 · browser-extension: 1
I need to control a desktop computer: Agents that see the screen and work the mouse and keyboard on a desktop, the way a person does. Picked from listings that mention computer use, desktop, mouse or screen in their name, description, tags or skills; those in Browser & Computer Use, or with API or MCP access, rank higher. Best fits with why: /tasks/control-a-computer · without the task: /browse?official=1
results
ui-tars-desktopbrowser-computercli+apimicrosoft-ufobrowser-computercliclaude-coworkautonomous-agentsapiagent-tarsbrowser-computerclichrome-devtools-mcpbrowser-computermcpfirefox-devtools-mcpbrowser-computermcp+cliartemisbrowser-computerclifigma-mcp-servercode-devtoolsmcppage-agentbrowser-computermcp+browser-extensionsafari-mcpbrowser-computermcp