What is FlaUI-MCP copilot-instructions.md?

Repository instructions for a Windows desktop automation MCP server. MCP is a standard way for an AI assistant to call tools, and this server exposes structured controls for Windows applications.

Use them when developing or maintaining Windows app automation tools, understanding the server architecture, adding MCP operations, or launching and controlling desktop applications.

They explain how the project works and how assistants should use accessibility-based element references instead of guessing positions from screenshots.

How shanselman/FlaUI-MCP configures GitHub Copilot

Reuse

Borrowing it

Nothing to install: this file belongs to shanselman/FlaUI-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/shanselman/FlaUI-MCP/main/.github/copilot-instructions.md

Clone the repo

git clone --depth 1 https://github.com/shanselman/FlaUI-MCP

Made for: GitHub Copilot.

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/shanselman/flaui-mcp/copilot-instructions/github.svg)](https://agentmods.dev/instructions/shanselman/flaui-mcp/copilot-instructions)

Your own site

<a href="https://agentmods.dev/instructions/shanselman/flaui-mcp/copilot-instructions"><img src="https://agentmods.dev/badge/instructions/shanselman/flaui-mcp/copilot-instructions/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

Your own site · 80×15

<a href="https://agentmods.dev/instructions/shanselman/flaui-mcp/copilot-instructions"><img src="https://agentmods.dev/badge/instructions/shanselman/flaui-mcp/copilot-instructions.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 2,495 This file is loaded in full into every session.

When invoked 2,495 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 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	$0.02495	$0.02495
Opus 5.5	$0.00998	$0.00998
Sonnet 5.5	$0.00499	$0.00499
Haiku 4.5	$0.00249	$0.00249

Measured 2mo ago against content hash 785af3172e74, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

FlaUI-MCP copilot-instructions.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 2mo 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.

.github/copilot-instructions.md · 318 lines

How it starts

The opening of the file, as written. The whole thing — 318 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Windows App Automation MCP Server

An MCP server that lets AI agents interact with Windows desktop applications using the same patterns as Playwright's browser automation - structured accessibility snapshots with element refs, not screenshot-based guessing.

Why MCP Server (not CLI or library)

Approach	Agent Experience
MCP Server	`windows_snapshot` → structured tree with refs → `windows_click ref="btn7"` ✅
CLI exe	Run command → parse text output → figure out element IDs → run another command
Screenshot-only	Take screenshot → vision model guesses coordinates → hope click lands

The Playwright MCP pattern works extremely well for agents:

browser_snapshot returns an accessibility tree with refs like [ref=s1e5]
Agent picks element by semantic meaning, not coordinates
browser_click ref="s1e5" is precise and reliable

This project brings that same pattern to Windows desktop apps.

Architecture

┌─────────────────────────────────────────────────────────────────┐
│  AI Agent (GitHub Copilot, Claude, etc.)                        │
│  - Calls MCP tools: windows_snapshot, windows_click, etc.      │
│  - Sees structured element tree, picks refs by meaning          │
└─────────────────────────────────────────────────────────────────┘
                              │ MCP Protocol (JSON-RPC over stdio)
                              ▼
┌─────────────────────────────────────────────────────────────────┐
│  Windows MCP Server (.NET / FlaUI)                              │
│  - Implements MCP tool handlers                                 │
│  - Translates UI Automation tree → agent-friendly snapshot      │
│  - Manages element refs ↔ AutomationElement mapping             │
└─────────────────────────────────────────────────────────────────┘
                              │
                              ▼
┌─────────────────────────────────────────────────────────────────┐
│  FlaUI (.NET) - github.com/FlaUI/FlaUI                         │
│  - UIA3Automation (WPF, UWP, Store Apps, modern Win32)         │
│  - UIA2Automation (fallback for older WinForms)                │
│  - Handles platform quirks, control patterns, tree walking      │
└─────────────────────────────────────────────────────────────────┘

Read the full file on GitHub · 318 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.

2mo ago First seen · 318 lines · 2,495 tokens per session scan A 785af3172e74

Subscribe to this mod's changes

FlaUI-MCP copilot-instructions.md is an instructions file published in the GitHub repository shanselman/FlaUI-MCP (110 stars, last pushed 4mo ago), licensed MIT. It adds 2,495 tokens to every session, about $0.0100 per session on Opus 5.5. 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.

FlaUI-MCP copilot-instructions.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
FlaUI-MCP copilot-instructions.mdshanselman/FlaUI-MCP	Instructions file	110	4mo ago	MIT	A	2,495	GitHub Copilot
vscode buildNext.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	9,719	GitHub Copilot
next.js AGENTS.mdvercel/next.js	Instructions file	143k	today	MIT	A	7,461	Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchain	Instructions file	149k	yesterday	MIT	A	4,680	Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	5,516	GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	3,093	GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness	Instructions file	274k	2d ago	MIT	A	4,313	Codex, OpenCode

FlaUI-MCP: Instructions file for GitHub Copilot