"Methods or tools to control a computer system" matching MCP servers:

Enables AI agents to drive a real headful Chrome browser using vision-first computer interactions, with support for multi-agent tab groups, password-manager-filled logins, and human handoff.

Enables AI agents to use a desktop computer with event-driven settling, waiting for the screen to react and stabilize before returning a settled screenshot and verdict.

Enables coding agents to ask what a window shows and receive a concise JSON answer from a local Ollama model instead of ingesting the full accessibility tree, reducing token usage. It is read-only and supports optional session context, health checks, and model release.

Enables low-cost agent models to control Windows applications through a compact, state-safe proxy over Open Computer Use, reducing model-visible context by up to 99.8% with support for record/replay and reusable UI component memory.

Lets any number of concurrent Claude Code sessions drive a Firefox browser through the Browser Control extension by funneling every session's commands over a single shared port via a background daemon and private unix socket. Sessions no longer have to compete for a limited pool of extension ports, and requests stay isolated through per-request correlation ids.

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

A local MCP server that lets compatible agents use the official, signed Computer Use broker bundled with the OpenAI ChatGPT macOS app.

Enables self-hosted AI gateway and agent control plane with governed MCP tools, virtual-key budgets, caching, and audit, supporting OpenAI, Anthropic, Gemini, MCP, and A2A protocols. It provides deterministic prompt enhancement and governed execution with a zero-credential first run.

Enables MCP agents to drive the user's already-open Chrome profile through a Manifest V3 extension and loopback bridge, listing and controlling existing tabs, capturing screenshots, and sending clicks, typing, drags and key holds via an independent on-page cursor without moving the system mouse. It also supports form filling, console and network inspection, read-only or confirmed JavaScript execution, file and PDF downloads, and game-style screenshot/action loops with snapshot recovery and an emergency stop.

Enables LLMs to orchestrate AI agents and tasks, inspect DAG workflows, monitor cluster metrics, and perform safe database queries and statements through standardized MCP tools.

Enables AI coding agents to request a second opinion from a different frontier model via a single tool call, with PII scrubbed before transit, live web search, and support for Claude, ChatGPT, Cursor, and Gemini.

Enables users to deploy a production-grade control plane for agents, providing a spec-compliant MCP server, scoped tool grants, failure-mode detection, and cost governance.

Enables AI agents to request an independent second opinion from a different frontier model, with PII scrubbing before transit, live web search grounding, caching, and multi-provider failover.

Enables AI assistants to operate a real, logged-in Firefox session through an extension, including tab and history management, page reading, screenshots, and clicking, typing, or scrolling on domains the user approves.

Enables an AI assistant to run tasks on a hosted cloud desktop that belongs to the user, with a browser that stays signed in to their accounts, its own email address, and its own files, so it can fill forms, download and edit documents, and carry out long jobs that outlast a chat reply, returning answers with screenshots and recordings. It also exposes tools for checking current activity, task history, sent mail, interrupting a run, and saving or recalling notes, reached over OAuth-authenticated Streamable HTTP or a stdio bridge.

Serves a loopback-only MCP endpoint that lets a same-machine client start, steer, and cancel DSH Sessions it knows by id, list their durable subagent trees, deliver messages to continuable children, and read durable event logs with paging and chunked oversized-event recovery. It maps every call onto native Session Controller and subagent services without owning task state, starting a second listener, or registering model-facing tools.

Enables local/remote execution infrastructure through the official Codex Runtime, providing shell, files, Git, sessions, browser, computer use, recoverable tasks, multi-host routing, dynamic MCP integration, and skill lifecycle management.

A native MCP server that gives AI assistants full Chrome control via the DevTools Protocol and an unpacked extension, including semantic element refs, real input, screenshots, and browser/tab/window management. It exposes 43 callable tools with a visible control overlay and an optional read-only security profile.

An MCP server paired with a Firefox extension that enables LLM clients to control the user's browser, supporting tab management, history search, and content reading.

Enables one coding agent to inspect, configure, debug, and repair another agent over stdio MCP, with redacted reads and confirm-gated writes and restarts.