EYRA
Enables observing and controlling Brave browser windows through Windows UI Automation/OCR, including reading UI element maps and performing mouse and keyboard actions.
Allows observing and interacting with Discord's desktop window through Windows UI Automation, including reading UI elements and clicking or typing.
Supports observing and interacting with Electron desktop applications via the Windows accessibility tree, with examples such as VS Code, Discord, Slack, and Telegram.
Enables observing and controlling Firefox windows through Windows UI Automation/OCR, including reading UI element maps and performing mouse and keyboard actions.
Enables observing and controlling Chrome windows through Windows UI Automation/OCR, including reading UI element maps, clicking controls, typing, and scrolling.
Allows observing and interacting with Slack's desktop window through Windows UI Automation, including reading UI elements and clicking or typing.
Allows observing and interacting with Telegram's desktop window through Windows UI Automation, including reading UI elements and clicking or typing.
This server does not currently have a deployable release on Glama. Follow the repository's setup instructions to install and configure it for your MCP client, including any required credentials and local dependencies.
https://github.com/user-attachments/assets/023b3238-3dee-4a1b-b20c-65e0447f14b8
Why EYRA?
Most computer-use agents send a full screenshot on every step and then guess pixel coordinates. EYRA reads what Windows already knows about the screen. Example see output (abridged):
WIN hwnd=0x3C051E proc=chrome.exe title="New repository - Google Chrome" mode=uia ms=22
#15 inp "Address and search bar" val="github.com/new" [158,46,1060,34]
#49 cmb "Owner" val="octocat" [325,333,150,32]
#51 inp "Repository name *" (focused) [496,333,530,32]
#68 chk "Add README" (unchecked) [978,682,42,24]Exact, not guessed. The text and coordinates come from the OS accessibility tree, so the agent doesn't have to estimate them from pixels.
click(id=51)hits the right control.Fewer tokens. A text map of the UI is cheaper than a screenshot.
see_diffreturns only what changed, typically under 40 tokens per step.Not just the web: the whole Windows desktop. Any browser (Chrome, Edge, Firefox, Brave; including logged-in tabs), File Explorer, Office, Settings, Notepad, Electron apps (VS Code, Discord, Slack, Telegram), canvases, games and video (through OCR). No browser extension, per-site API or cloud service.
Model-agnostic. It is a standard MCP server, so the same binary serves Gemini, Claude, GPT-based hosts or your own agent. Models that accept audio input (for example Gemini) can listen to the WAV clips that
listen/watchproduce. Text-only models still get Eye + Action.Zero runtime dependencies. No Python, FFmpeg, Whisper or API keys. Only Windows APIs: UI Automation, WinRT OCR, WASAPI and SendInput.
Safe by default. Password values are masked, password managers are blocked, there's a
--read-onlymode, a failsafe corner, a kill-switch hotkey and an audit log.
Related MCP server: windows-computer-use-mcp
Measured performance
Measured on Windows 10 at 1366×768 with eyra bench and the MCP server.
Latency of see (one window)
Mode | Chrome (GitHub page, ~100 elements) | Electron desktop app |
MCP server, warm ( | 22 ms | ~25 ms |
MCP server, warm ( | 23 ms | ~25 ms |
CLI, one-shot process | ~45 ms | ~65 ms |
OCR mode ( | ~80 ms | ~80 ms |
File Explorer showing a very large folder is the slowest case tested: ~195 ms.
Tokens per observation
Each window is compared with one screenshot of the same window (image tokens = w·h/750). Text tokens are estimated as chars/4.
Window (screenshot cost) |
|
|
|
|
Chrome, dense GitHub repo page, 1036×701 (~969) | ~1,137 | ~1,065 | ~901 (−7%) | ~42 (−96%) |
Electron desktop app, 1366×728 (~1,326) | ~675 | ~603 | ~528 (−60%) | ~28 (−98%) |
Windows desktop / Explorer, 1366×768 (~1,399) | ~294 | ~294 | ~250 (−82%) | ~31 (−98%) |
How to read this:
The first look at a very dense web page costs about as much as a screenshot, but it gives exact
#ids and coordinates instead of pixels to guess.The big savings come from the steps after that. A 20-step task that observes with
see_diffcosts about 900 + 19×40 ≈ 1.7k tokens instead of about 19–26k with screenshots.
Run it on your own machine:
eyra bench --window ChromeWhen to use EYRA (and when not)
Task | Best tool |
Native Windows apps (Explorer, Office, Settings, Telegram, WinForms/WPF/UWP) | EYRA |
Electron apps (VS Code, Slack, Discord, Teams) | EYRA |
Repeatedly watching the same window for changes | EYRA |
Canvas, games, remote desktop, video | EYRA |
Hearing system audio or the microphone (for audio-capable models) | EYRA |
Deep web automation: hidden DOM, network, console, JS | A browser-extension tool (DOM access beats OS-level access here) |
EYRA can only see what's on screen. It can't read DOM nodes that aren't rendered, network traffic or a page's JavaScript state.
Install
Download (recommended)
Download
eyra.exefrom the latest release. Or take the.zip, which also includesSKILL.md, the example MCP config and the license.Put it anywhere, for example
C:\Tools\eyra\eyra.exe. Nothing else needs to be installed: it runs on a stock Windows 10/11.Connect it to your agent (see below).
The binary isn't code-signed yet, so Windows SmartScreen may show a warning on first run: choose More info → Run anyway. You can check the download against the SHA-256 published with the release:
Get-FileHash .\eyra.exe -Algorithm SHA256Build from source
Requirements: Windows 10/11 and a stable Rust toolchain. The repo pins stable-x86_64-pc-windows-gnu, which needs MinGW-w64. To use MSVC instead, delete rust-toolchain.toml.
cargo build --release
# -> target\release\eyra.exe (~1.9 MB, no DLLs needed)
cargo test --releaseConnect it to an agent
EYRA speaks standard MCP over stdio, so the setup is the same everywhere: point the host at eyra.exe mcp.
Host | Where to add it |
Gemini – Antigravity | MCP servers → Manage → View raw config ( |
Gemini CLI |
|
Claude Code |
|
Claude Desktop |
|
Cursor / VS Code / others | the host's MCP config file, add the JSON below |
{
"mcpServers": {
"eyra": { "command": "C:\\path\\to\\eyra.exe", "args": ["mcp"] }
}
}Use "args": ["mcp", "--read-only"] to expose only the Eye, Ear and Watch tools, with no mouse or keyboard.
The server negotiates MCP revisions 2025-06-18, 2025-03-26 and 2024-11-05. It sends usage instructions on initialize and marks every tool with readOnlyHint/destructiveHint annotations, so hosts can auto-approve observation tools and ask before input actions.
Agent skill. SKILL.md teaches an agent the lowest-token workflow.
MCP tools (16)
Eye
Tool | What it does | Key arguments |
| Visible windows: hwnd, process, title, rect, flags | — |
| Numbered UI element map (UIA, OCR fallback); includes open popup menus |
|
| Only | same as |
| Compact JPEG/PNG, including occluded windows |
|
| Blocks until the pixels change (page load, animation end) |
|
Ear and Watch
Tool | What it does | Key arguments |
| Output (loopback) and input endpoints | — |
| Records system audio, the mic, or both, trims silence, saves a 16 kHz WAV |
|
| Rolling timeline of scene-change keyframes and audio clips |
|
Action (disabled in --read-only)
Tool | What it does | Key arguments |
| Clicks by |
|
| Types Unicode text (background UIA |
|
| Sends a keyboard shortcut such as |
|
| Scrolls the mouse wheel or drags with the left button |
|
| Restores, focuses and optionally locks a default target window |
|
Reading the element map
#12 btn "Save" (disabled) [840,610,90,32]
│ │ │ │ └ x,y,width,height in screen pixels
│ │ │ └ state: focused, disabled, checked, unchecked, mixed, selected
│ │ └ accessible name (val="…" follows when an input has a value)
│ └ role: btn inp lnk chk rad cmb tab mnu itm sld hdr txt img doc pwd ocr el
└ id: pass it to click / type_textWith coords="center" the position is printed as the click point only (#12 btn "Save" (disabled) @885,626), which is the cheapest format.
#ids come from the most recent see/see_diff of that window, so call see_diff again after the UI changes. Open popup menus (File/Edit menus, context menus) are part of the window's map.
CLI
eyra windows
eyra see --window Chrome --interactive-only --coords center
eyra diff --window Chrome
eyra screenshot --window Chrome --som --out som.jpg
eyra click --id 5
eyra type "hello world" --id 2 --enter
eyra hotkey ctrl+l
eyra wait-change --window Chrome
eyra audio-devices
eyra listen --seconds 8 --source both
eyra watch --window Chrome --duration 60
eyra ocr-langs
eyra logs --tail 25
eyra bench --window Chrome
eyra serve --port 47821 # optional 127.0.0.1 HTTP bridge (token-authenticated)--window accepts an hwnd (0x3C051E), a title substring, a process name or screen. Add --json for machine-readable output.
Safety
Guard | Behaviour |
Password fields | Values are always shown as |
Sensitive windows | 1Password, KeePass, Bitwarden and Windows Security can't be read or controlled unless you pass |
| Removes all input tools from the MCP tool list and rejects them in the CLI and bridge |
Corner failsafe | Moving the mouse to the top-left corner |
Kill switch |
|
Dangerous hotkeys |
|
Audit log | JSONL at |
Troubleshooting
Symptom | Cause and fix |
| Restore it first with |
| There is no UIA tree there. Use |
OCR misses your language | Run |
Clicks or typing do nothing in an admin window | Windows UIPI blocks input to elevated windows from a non-elevated process. Run eyra elevated, or the target app non-elevated. |
Coordinates are off on a multi-monitor or 150% DPI setup | eyra is per-monitor DPI aware and coordinates are physical pixels. Use |
Environment variables
Variable | Effect |
| Audit log path / disable logging |
| Forces read-only mode |
| Upscales frames before OCR (slower; can help with very small text) |
Architecture
src/
├─ eye/ uia.rs (cached UIA subtree scan) · ocr.rs (WinRT OCR) · capture.rs (PrintWindow/BitBlt)
│ diff.rs (element and pixel diff) · som.rs (Set-of-Mark badges) · windows.rs
├─ ear/ wasapi.rs (loopback + mic) · vad.rs (resample + energy VAD) · wav.rs
├─ hand.rs UIA patterns → SendInput fallback
├─ watch.rs ring-buffered video and audio timeline
├─ mcp.rs stdio JSON-RPC server ├─ bridge.rs local HTTP bridge
├─ safety.rs · audit.rs · state.rs └─ cli.rsLicense
Licensed under the Apache License 2.0.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
This server cannot be deployed
Maintenance
Related MCP Connectors
MCP server for your apps' tools and custom tools, plus hosted AI agents and approval-gated workflows
Nifty's MCP server — exposes tasks, projects, messages, and files as tools for AI agents.
Remote MCP server exposing your Node Command fleet (files, shell, processes, browser) to AI hosts.
A comprehensive Model Context Protocol (MCP) server that enables AI assistants to interact with yo…
Related MCP Servers
- AlicenseNot gradedqualityBmaintenanceAn MCP server that gives any AI assistant eyes and hands on your desktop — screenshots, clicking, typing, OCR, window management, accessibility-tree queries, workflow recording.5Apache 2.0
- FlicenseNot gradedqualityDmaintenanceA local, dependency-free MCP server that gives AI agents controlled access to the active Windows desktop, enabling automated interaction with applications through screenshots, clicks, typing, and window management.1-
- FlicenseNot gradedqualityBmaintenanceMCP server that lets an LLM see and drive any running Windows app: attach a window, screenshot it, read its UI Automation tree, and send clicks, typed text, and key presses with pixel coordinates.-
- FlicenseNot gradedqualityDmaintenanceMCP server that enables AI agents to control Windows by clicking, typing, and navigating with a visible cursor overlay, using a layered approach (native UIA, browser CDP, pixel fallback) for reliable interaction.1-