Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type @ followed by the MCP server name and your instructions, e.g., "@jharokha read my remote desktop window and summarize the text"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
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).
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
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 PNG. |
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": "05/10", "to": "11/10"}'. --window-title picks the window when more than one session is open.
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; 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).
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 and exit code, read up to an end marker it prints. |
| Prints the ASCII alphabet once and learns the terminal's font, so terminal reads are exact cell by cell instead of OCR. |
| Write a file through the shell; go to a URL; click buttons in order. |
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.
On a live Windows 365 session, a week of a Teams group chat read into a timeline by a fresh headless Claude Code with jharokha as its only tools: 22 calls and 2 m 47 s by hand-driven scrolls and reads (v0.23.1); 8 calls, one teams.messages call per week (v0.24.1). How it is tested: DEVELOPMENT.md.
RDP sends no frames to a minimized window; covered is fine.
Windows OCR confuses lookalikes (0/O, 1/l); verify re-reads lines with a second engine. A terminal is read by matching its cells against glyphs learned from the screen (run terminal.glyphs once a session), 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 and spots hold at the size and zoom they were measured at.
Apps are recognised by their English UI text.
Windows only; a port would sit beside src/jharokha/win/ and reuse core/.
MIT.
This server cannot be deployed
Connect ChatGPT, Claude, Cursor or VS Code to your Windows PC: files, terminal, browser, apps.
Remote Desktop Commander: use files, terminal and processes on your own computers from any AI app.
Hosted browser for agents: open pages, search the web, extract data, read PDFs and take screenshots.
Agent tools: clean web screenshots/PDFs, PDF & image OCR to Markdown, PageSpeed audits, email checks
