What is computer-use-mcp AGENTS.md?

Setup and usage instructions for computer-use-mcp, a tool that lets AI agents interact with computers on macOS, Windows, and Linux. They cover desktop control, form filling, scripting, recovery, and Windows administration profiles.

Use them to configure computer-use-mcp, automate desktop actions, fill forms, recover from focus problems, or handle supported Windows administration tasks.

They help an agent choose the right way to perform desktop tasks and keep filesystem access within configured boundaries. They also document how to prepare the tool for different operating systems.

How zavora-ai/computer-use-mcp configures Codex and OpenCode

Reuse

Borrowing it

Nothing to install: this file belongs to zavora-ai/computer-use-mcp. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/zavora-ai/computer-use-mcp/main/AGENTS.md

Clone the repo

git clone --depth 1 https://github.com/zavora-ai/computer-use-mcp

Made for: Codex, OpenCode.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/zavora-ai/computer-use-mcp/agents-md.svg)](https://agentmods.dev/instructions/zavora-ai/computer-use-mcp/agents-md)

Your own site

<a href="https://agentmods.dev/instructions/zavora-ai/computer-use-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/zavora-ai/computer-use-mcp/agents-md.svg" alt="Measured on agentmods" height="20"></a>

Per session 5,570 This file is loaded in full into every session.

When invoked 5,570 The same file — it is already loaded in full.

Security scan B 1 finding. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

Model	Per session	Once invoked
Fable 5.1	$0.05570	$0.05570
Opus 5	$0.02785	$0.02785
Sonnet 5	$0.01114	$0.01114
Haiku 4.5	$0.00557	$0.00557

Measured 8d ago against content hash 3631520d557c, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade B, and why

computer-use-mcp AGENTS.md scanned grade B with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 8d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Reads agent configuration directoriesmediumAgent snooping

.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.

Codex reads local MCP servers from `~/.codex/config.toml`:

AGENTS.md · 602 lines

How it starts

The opening of the file, as written. The whole thing — 602 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Using computer-use-mcp with AI Agents

This guide covers how to integrate computer-use-mcp into AI agent frameworks and agentic workflows. Works on macOS, Windows, and Linux.

Skills (recommended): copy from skills/ in this package into your agent skills directory:

skills/computer-use — when/how to use desktop control
skills/computer-use-forms — accessibility form fill
skills/computer-use-scripting — AppleScript / PowerShell first
skills/computer-use-recovery — FocusFailure recovery
skills/computer-use-windows-admin — filesystem / registry / process

MCP prompts: diagnose-desktop, fill-form, script-first, safe-desktop-task
Profiles: COMPUTER_USE_PROFILE=core|ax|scripting|windows-admin|full (default full)

v7 environment & behaviors:

COMPUTER_USE_FS_ROOTS — confine the filesystem tool to comma-separated absolute roots (blocks ../symlink escape). Unset = unrestricted.
COMPUTER_USE_NATIVE_PATH — override native .node resolution (else: separately installed platform package → bundled binary).
COMPUTER_USE_LEGACY_FOCUS_TAG=true — restore the legacy [focusRequired: X] description suffix (off by default in v7; still in _meta / get_tool_metadata).
COMPUTER_USE_STRUCTURED_CONTENT=false — legacy text-only results (omits structuredContent + outputSchema).
Cancellation: tool calls honor the host AbortSignal (wait returns early; run_script terminates its subprocess tree through a POSIX process group or recursive Windows taskkill).
Progress: long filesystem searches emit notifications/progress when a progress token is present.

v7.1 MCP behavior:

Legacy MCP clients continue through initialize; no tool names or v7 input schemas changed.
MCP 2026-07-28 clients use stateless requests, server/discover, per-request identity/capabilities, cache hints, MRTR, and subscriptions/listen.
The io.modelcontextprotocol/tasks extension is opt-in and server-directed for selected long-running read-only calls. Extension-aware hosts poll tasks/get; stock clients should omit the extension capability and receive synchronous results.
computer-use-mcp-http serves the bundled loopback-only HTTP endpoint. Remote hosts must embed createComputerUseHttpHandler, validate OAuth themselves, and pass only verified authInfo.
Tool annotations are descriptive hints, never an authorization boundary.

Read the full file on GitHub · 602 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

8d ago First seen · 602 lines · 5,570 tokens per session scan B 3631520d557c

Subscribe to this mod's changes

computer-use-mcp AGENTS.md is an instructions file published in the GitHub repository zavora-ai/computer-use-mcp (45 stars, last pushed 16d ago), licensed MIT. It adds 5,570 tokens to every session, about $0.0278 per session on Opus 5. A static security scan graded it B with 1 finding (reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Browser automation

next.js AGENTS.md

AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.

vercel/next.js · 7,296 tokens

codex AGENTS.md

AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.

openai/codex · 5,153 tokens

vscode buildNext.instructions.md

Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).

microsoft/vscode · 6,785 tokens

computer-use-mcp: Instructions file for Codex