Windows-MCP CLAUDE.md

Windows-MCP CLAUDE.md is an instructions file for Claude Code from CursorTouch/Windows-MCP. It costs 1,930 tokens per session, scanned A, original, MIT.

A repository guide for Claude Code that explains a Windows-MCP project, its desktop-control tools, commands, architecture, and coding style.

In plain words
What is it for?
Use it when working on the Windows-MCP Python server, such as running it, formatting or checking code, or finding the right desktop-automation tool.
Why use it?
It gives the coding agent the project context and working rules it needs before changing code.

Instructions file for Claude Code

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

About the project

Windows-MCP is an MCP server that lets AI agents operate Windows computers through actions such as navigating files, opening applications, controlling windows, and interacting with user interfaces. It is used for desktop automation, software testing, and other tasks that require an agent to use Windows.

CursorTouch/Windows-MCP · 6,910 stars · on GitHub

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add instructions/cursortouch/windows-mcp/claude-md
Clone the repo
git clone --depth 1 https://github.com/CursorTouch/Windows-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 Windows-MCP CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/cursortouch/windows-mcp/claude-md.svg)](https://agentmods.dev/instructions/cursortouch/windows-mcp/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/cursortouch/windows-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/cursortouch/windows-mcp/claude-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 1,930 This file is loaded in full into every session.
When invoked 1,930 The same file — it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
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.

ModelPer sessionOnce invoked
Fable 5.1 $0.01930 $0.01930
Opus 5 $0.00965 $0.00965
Sonnet 5 $0.00386 $0.00386
Haiku 4.5 $0.00193 $0.00193

Measured 6d ago against content hash 0e4bb834de42, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

Windows-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 6d 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 · 89 lines

How it starts

The opening of the file, as written. The whole thing — 89 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

Windows-MCP is a Python MCP (Model Context Protocol) server that bridges AI LLM agents with the Windows OS, enabling direct desktop automation. It exposes 20 tools via FastMCP:

Group Tools
Capture Screenshot, Snapshot, Scrape, DisplayInventory
Input Click, Type, Scroll, Move (also drag-and-drop via drag=True), Shortcut, MultiSelect, MultiEdit
Timing Wait, WaitFor
System App, PowerShell, FileSystem, Registry, Process, Clipboard, Notification

Tool names are defined by the name= argument of each @mcp.tool(...) in src/windows_mcp/tools/; that directory is the source of truth. Note the shell tool is registered as PowerShell, not Shell. Any subset can be removed at startup with --disable-tools (e.g. --disable-tools PowerShell,Registry).

Build & Development Commands

uv sync                    # Install dependencies
uv run windows-mcp         # Run the MCP server
ruff format .              # Format code
ruff check .               # Lint code
ruff check --fix .         # Lint and auto-fix
pytest                     # Run all tests
pytest tests/test_foo.py   # Run a single test file

Package manager: UV (not pip). Python: 3.13+. Build backend: Hatchling.

Architecture

The codebase follows a layered service architecture under src/windows_mcp/:

Entry point__main__.py: Builds the FastMCP server, parses CLI flags, and selects the transport. Tool registration is delegated to tools.register_all(); an async lifespan initializes the Desktop, WatchDog, and Analytics singletons, which tools resolve lazily through the get_desktop / get_analytics callables.

Tools layertools/: One module per tool group, each exposing register(mcp, *, get_desktop, get_analytics). tools/__init__.py holds the module list and register_all(). Tool functions are thin — they normalize arguments and delegate to a service package. The @with_analytics decorator wraps each one for telemetry, making it the existing precedent for cross-cutting concerns at the tool boundary.

Read the full file on GitHub · 89 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. 6d ago First seen · 89 lines · 1,930 tokens per session scan A 0e4bb834de42

Subscribe to this mod's changes

Windows-MCP CLAUDE.md is an instructions file published in the GitHub repository CursorTouch/Windows-MCP (6,910 stars, last pushed yesterday), licensed MIT. It adds 1,930 tokens to every session, about $0.0097 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.