jharokha
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.
jharokha
jha·ro·kha /dʒʱəˈroː.kʰaː/ noun
An overhanging window of Indian palaces, used to watch the street without being seen.
From Hindi jharokhā (झरोखा).
jharokha lets AI agents (Claude Code, Claude Desktop / Cowork, any MCP client) work in a Windows remote-desktop session they can't otherwise reach: Windows 365 or Azure Virtual Desktop in Windows App, an mstsc RDP window. It reads the session window as text with local OCR and, only if started with --allow-input, scrolls, clicks, types and presses keys in it. Nothing is installed in the session; it works from the pixels you already see.
Reads what an agent needs: a Teams chat as messages (time, sender, text, quote), an inbox as mails, a screen as text in reading order; not screenshots.
Small and fixed: eight tools whatever apps and actions are loaded; a new app or action is data, never a tool. About 3k tokens of tool descriptions a session.
Safe by default: read-only unless you opt in; input only to the app it was meant for, never an app's sending keys unless asked, never while you or another agent use the session. Screen text is untrusted data.
Private: nothing on disk unless asked (
--trace,--capture), no network, no telemetry.
Windows 10 2004+ / 11. Needs an OCR language pack (any Windows display language has one).
Install
claude mcp add --transport stdio --scope user jharokha -- uvx --from git+https://github.com/ibrarwtf/jharokha jharokhaAdd --allow-input at the end to let it act. From a checkout: uv run --no-sync --project PATH jharokha (without --no-sync, a second client session fails to start while the first holds jharokha.exe).
Related MCP server: opencode-gui-bridge
Tools
Screen text comes back inside <screen_text source="ocr" untrusted="true">. Coordinates are client-area pixels.
Tool | What it does |
| Is there a session window and can it be read; which app and view is in front, with a confidence; what would stop input. |
| The apps, their views and named regions, and every action with its arguments and risk. |
| A region as text or items: the app's focus region by default (a Teams thread), |
| One thing by text, regex or where it is ( |
| Until a text appears or goes, or the screen holds still. |
| An action in one call with a structured result (below). Without |
| With |
| The last resort: a WebP image. |
The same verbs run in a shell, each the tool called in-process: jharokha status, jharokha read --region teams.thread, jharokha --allow-input do teams.messages --args '{"from": "18/03", "to": "21/03"}'. --window-title picks the window when more than one session is open.
Apps and actions
An app is data (src/jharokha/apps/*.toml): the text and panes it is recognised by, its views, their named regions and how each is read, and its input policy. Built in: Windows Terminal, Teams, Outlook, a browser, Windows' search panel; anything else is generic, read by panels. Calibration for your screen (zoom variants, the taskbar icons as spots so actions can switch apps) goes in a git-ignored apps.toml (--apps PATH; see apps.example.toml). So does a people map, [people.<id>] and [chats.<id>] with the names the screen shows each by: the Teams actions then take an id (chat = "team") and find that chat in the list and header under any of its names, cut short or not. The messages jharokha_read and the Teams actions return then also carry who (the sender's id), day (ISO) and time as HH:MM (~HH:MM when borrowed from the message above).
An action is a checked sequence of steps run by jharokha_do (src/jharokha/apps/actions/*.toml; your own go in apps.toml):
Action | What it does |
| The messages from one day to another, oldest first, scrolling back to |
| Open a chat; type a draft and never send. |
| A folder's unread mails; one mail's reading pane. |
| A command's output, exit code and status, read up to the shell's next state prompt; long output paged back from the shell. |
| A page of a file's lines, numbered; a file written from this machine's clipboard and checked by its SHA-256, nothing of it typed. |
| Prepares the PowerShell tab: a prompt that shows the command counter, date, time, status, exit code and directory, no colours or predictions, and the font learned from the alphabet it prints. Only this action prepares a tab: the others refuse a tab without the prompt ( |
| A run that outlived its timeout, waited for up to 1800 s; a page of the last command's output. |
| Replace text in a file only where it occurs exactly once, through the clipboard. |
| What came into a chat since its last check; the newest messages on screen. |
| Bring an app forward by its taskbar icon; when the icon opens a picker of the app's windows, the one titled like |
| Go to a URL; click buttons in order. |
Input safety
Every input, from act, an action or the shell, passes these checks first; a refusal sends nothing and says what to do next.
Check | Refusal | Prevents |
The expected app is in front ( |
| A command typed into a browser and searched for on the web |
The app's policy: sending keys (Enter in Teams, Ctrl+Enter in Outlook, Enter in a browser) need |
| A half-written message sent |
One agent at a time per session window |
| Two agents typing into one session |
You haven't used this computer's keyboard or mouse in the last 3 s, and stop it while text is sent |
| Your keystrokes mixing into the agent's |
The point is not covered by another window |
| Clicks lost under this computer's taskbar |
--trace PATH records every input (typed text as a hash unless --trace-text). --capture DIR saves each screen an action or tool reads, for replaying readers offline; it holds real screen content, so keep it out of any repository.
Testing
An action does in one call what an agent would otherwise do in many scrolls and reads: teams.messages reads a chat from one day to another in a single call. How it is tested: DEVELOPMENT.md.
Limits
RDP sends no frames to a minimized window; covered is fine.
Windows OCR confuses lookalikes (
0/O,1/l);verifyre-reads lines with a second engine. A terminal is read by matching its cells against glyphs learned from the screen (terminal.setup, once per tab), so it has no lookalike problem; a glyph it has not seen is read by the second engine and counted as unknown.Keep the session window one size: calibration holds at the size and zoom it was measured at. Taskbar spots follow a resize when
[calibration.session]has thesizethey were measured at.Apps are recognised by their English UI text.
Windows only; a port would sit beside
src/jharokha/win/and reusecore/.
Licence
MIT.
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
Connect ChatGPT, Claude, Cursor or VS Code to your Windows PC: files, terminal, browser, apps.
Give your agent eyes: screenshots of any web page it can see, pages as markdown, and PDFs.
Remote Desktop Commander: use files, terminal and processes on your own computers from any AI app.
A real browser for your agent: screenshots, page checks, Markdown and PDFs.
Related MCP Servers
- AlicenseNot gradedqualityCmaintenanceEnables comprehensive Windows desktop automation including screen capture, OCR text extraction, mouse/keyboard control, window management, process control, and clipboard operations through 25+ tools for AI agents.55 PyPI8MIT
- FlicenseNot gradedqualityDmaintenanceEnables AI assistants to control Windows GUI by listing and focusing windows, capturing element snapshots via UIA/OCR/CDP, performing clicks/inputs/scrolls, verifying changes, waiting for screen updates, taking screenshots, and obtaining visual descriptions.2-
- FlicenseNot gradedqualityCmaintenanceEnables AI agents to see and operate a Windows PC through mouse, keyboard, screenshots, OCR, window control, and shell commands.-
- AlicenseNot gradedqualityCmaintenanceEnables AI agents to interact with and automate Windows desktop applications, providing UI inspection, mouse/keyboard control, OCR, and window management for QA tasks.MIT