computer-control-mcp: Instructions file for Claude Code

CLAUDE.md

computer-control-mcp CLAUDE.md is an instructions file for Claude Code from gzmagyari/computer-control-mcp. It costs 658 tokens per session, scanned A, original, from a forked repository, MIT.

Instructions for developing a Python MCP server that controls a computer with mouse, keyboard, screenshots, and text recognition. OCR, or optical character recognition, means reading text from an image.

In plain words
What is it for?
Developing and testing computer-control-mcp, running its server, taking screenshots, controlling windows, and building a distributable Python package.
Why use it?
They document the project layout and commands needed to install, run, test, and package the server.

Instructions file for Claude Code

Written for Claude Code: the file is CLAUDE.md. Also seen: mentions CLAUDE.md; mentions Claude Code.

This is gzmagyari/computer-control-mcp's own configuration. It tells Claude Code how to work on computer-control-mcp itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything computer-control-mcp configures →

Reuse

Borrowing it

Nothing to install: this file belongs to gzmagyari/computer-control-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/gzmagyari/computer-control-mcp/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/gzmagyari/computer-control-mcp

Made for: Claude Code.

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.

agentmods badge for computer-control-mcp CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/gzmagyari/computer-control-mcp/claude-md.svg)](https://agentmods.dev/instructions/gzmagyari/computer-control-mcp/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/gzmagyari/computer-control-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/gzmagyari/computer-control-mcp/claude-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 658 This file is loaded in full into every session.
When invoked 658 The same file — it is already loaded in full.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin fork From a forked repository.
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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00658 $0.00658
Opus 5 $0.00329 $0.00329
Sonnet 5 $0.00132 $0.00132
Haiku 4.5 $0.00066 $0.00066

Measured 7d ago against content hash 50e049e9ffc3, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

computer-control-mcp CLAUDE.md scanned grade A with 0 findings 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 7d 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.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

CLAUDE.md · 52 lines

How it starts

The opening of the file, as written. The whole thing — 52 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md

This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.

Project Overview

Computer Control MCP is a Python MCP (Model Context Protocol) server that provides computer control capabilities (mouse, keyboard, screenshots, OCR) using PyAutoGUI, RapidOCR, and ONNXRuntime. It is published on PyPI as computer-control-mcp.

Build & Development Commands

# Install in development mode (edits to source reflect immediately)
pip install -e .

# Run the MCP server
computer-control-mcp

# Run tests
python -m pytest

# Build distributable wheel (requires hatch: pip install hatch)
hatch build

Architecture

Source Layout (src/computer_control_mcp/)

  • core.py — The main module. Contains all MCP tool definitions (@mcp.tool() decorated functions), the FastMCP server instance (mcp), screenshot logic (MSS and Windows Graphics Capture), OCR processing via RapidOCR, and window matching (fuzzy via fuzzywuzzy, regex). This is the file you'll modify most often.
  • cli.py — CLI interface with subcommands (server, click, type, screenshot, list-windows, gui). Delegates to core.py tools via mcp.call_tool(). When no subcommand is given, runs the MCP server by default.
  • server.py — Thin wrapper that imports and runs main() from core.py.
  • gui.py — Tkinter-based GUI test harness for manual testing of click, type, and screenshot features.
  • __main__.py — Entry point for python -m computer_control_mcp, delegates to CLI.

Entry Points (defined in pyproject.toml)

  • computer-control-mcpcli.py:main (CLI with subcommands, default: run server)
  • computer-control-mcp-serverserver.py:main (direct server start)

Key Patterns

  • All MCP tools are registered on the module-level mcp = FastMCP("ComputerControlMCP") instance in core.py.
  • Window matching uses _find_matching_window() which supports both fuzzy matching (fuzzywuzzy partial_ratio) and regex matching.
  • Screenshots use mss library by default. On Windows, windows-capture (WGC) is optionally available for GPU-accelerated windows that render black with standard capture.
  • WGC auto-detection is configured via the COMPUTER_CONTROL_MCP_WGC_PATTERNS env var (comma-separated window title substrings).
  • Screenshot save directory is configurable via COMPUTER_CONTROL_MCP_SCREENSHOT_DIR env var, defaulting to OS downloads folder.
  • Logging goes to stderr in development (ENV=development) and stdout in production.

Read the full file on GitHub · 52 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.

  1. 7d ago First seen · 52 lines · 658 tokens per session scan A 50e049e9ffc3

Subscribe to this mod's changes

computer-control-mcp CLAUDE.md is an instructions file published in the GitHub repository gzmagyari/computer-control-mcp (0 stars, last pushed 5mo ago), licensed MIT. It adds 658 tokens to every session, about $0.0033 per session on Opus 5. A static security scan graded it A with 0 findings. It comes from a forked repository.

Related

Other instructions, from other repositories

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 · 5,182 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

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

langchain AGENTS.md

AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.

langchain-ai/langchain · 4,469 tokens

vscode oss-third-party-notices.instructions.md

Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).

microsoft/vscode · 5,001 tokens

spec-kit AGENTS.md

AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.

github/spec-kit · 7,104 tokens