ZBS Index What actually exists in applied AI, with the source next to it

mcp server

Glasswarp

Eyes and hands on real Windows PCs — observe, click, type via Glasswarp API.

Description as published by the maintainer. Source

  • version 0.1.0
  • active

active — Most recent push to the repository was 2026-08-01.

What this server can do

16 functions, named and described by the server itself. Parameter names are shown because they say more about what a function does than its name usually does.

app.launch(args, session_id, path_or_name)
Launch an executable on the remote Windows rig (name on PATH or absolute path), optional args. Side effects: starts a process; Glasswarp tracks it and closes it on session.end. Use for notepad.exe, mspaint.exe, chrome with URL args, etc. Wait/re-observe after launch before clicking — do not assume the window is focused immediately. Required: session_id, path_or_name.
demos.get(format, demo_id)
Return one showcase run contract (install, command, needs, framing). Does NOT execute the demo or control a PC. Call after demos.list when you know the demo_id. If the client can run shell, offer the command; if chat-only, show the card. Do not replace this with a slow MCP click loop for solver demos. Required: demo_id.
demos.list(format)
List showcase run contracts (id, title, install, command). Read-only catalog — does NOT start a session, touch a rig, or run solvers. Use when the user asks for Minesweeper/Mona Lisa/Paint demos or you need the glasswarp-demo command. Prefer demos.get for one full card. For ad-hoc UI work use rigs.list → session.start → screen.observe instead.
input.click_target(button, double, target_id, session_id)
Left/right/middle-click a UIA target by id from the latest screen.observe (uses native center coords). Prefer over input.click_xy. Side effect: real mouse click on the remote Windows desktop. Do not reuse target_id after the screen may have changed — re-observe first. For click→type→keys sequences, use input.send_actions (one turn) instead of chaining this tool. Required: session_id, target_id.
input.click_xy(x, y, button, double, session_id)
Click at native screen coordinates (0…native_width-1, 0…native_height-1 from screen.observe). Last resort when no suitable UIA target exists — prefer input.click_target. Never use JPEG/downscaled pixel coords. Side effect: real mouse click on the remote desktop. Required: session_id, x, y.
input.drag(to_x, to_y, from_x, from_y, session_id, duration_ms)
Press-move-release mouse drag in native capture coordinates. Use for drawing, sliders, selection boxes, and drag-and-drop. Side effect: mouse_down → moves → mouse_up on the remote desktop. Prefer input.send_actions if the drag is one step in a longer predictable sequence. Required: session_id, from_x, from_y, to_x, to_y.
input.scroll(x, y, delta, session_id)
Move the cursor to native (x,y) then apply a vertical mouse-wheel delta. Side effect: scroll on whatever is under that point. Negative delta scrolls toward the bottom of the page. Prefer input.send_actions when scroll is part of a multi-step sequence. Re-observe after scrolling lists/pages before clicking targets. Required: session_id, x, y, delta.
input.send_actions(actions, session_id, observe_after, observe_image)
PREFERRED multi-step tool: run 1–10 predictable UI actions in one call (input.click_target, input.click_xy, input.type_text, input.send_keys, input.drag, input.scroll). Side effects: all actions execute on the remote desktop; fails fast before sending if any action is invalid. observe_after defaults true (verification observe: text+targets; set observe_image=true for JPEG). Do not batch across unpredictable waits (page loads, installers, modals) — single-step those. Prefer this over chaining solo click/type/keys tools. Required: session_id, actions.
input.send_keys(keys, session_id)
Send a key or chord to the focused window (e.g. enter, tab, ctrl+s, alt+f4, win). Side effect: real key events on the remote desktop. Prefer bundling into input.send_actions when the shortcut follows a click/type in the same planned sequence. Use input.type_text for literal strings, not this tool. Required: session_id, keys.
input.type_text(text, session_id)
Type a Unicode string into the currently focused control via native input. Does not click first — focus the field (input.click_target / input.send_actions) before calling. Side effect: keystrokes on the remote desktop. For form fills (click → type → tab/enter), prefer input.send_actions in one call. Required: session_id, text.
rigs.list
List Windows machines (rigs) paired to this API key: id, name, online, api_access_enabled, and USABLE flag. Read-only — does not start a session. Call first before start_session. A rig is USABLE only when online AND the owner enabled API access. If none are USABLE, tell the user to install the host agent, pair in Console → Rigs, and enable API access — never ask for OS passwords.
screen.observe(mark, image, quality, max_width, session_id)
Read the current screen: UIA targets (numbered ids + native coords) and a text summary. Does not move mouse/keyboard. Default image=false (no JPEG) for speed; set image=true only when you must judge pixels visually (then max_width≈960, quality≈60). If changed=false, JPEG is omitted even when requested — do not re-analyze; wait or act differently. If dirty is null, assume changed. Prefer input.send_actions for multi-step UI; observe after meaningful steps, not after every click. Target ids are valid only until the next UI change. Required: session_id.
session.end(session_id)
End an active session. Side effects: stops billing, runs host safety_restore, closes apps launched via app.launch. Always call when finished or abandoning — do not leave sessions open. Safe to call once; further observe/input on that session_id will fail. Required: session_id.
session.live_view(session_id)
Return the console Live View URL (≈60fps) for the rig owner to watch and intervene. Read-only for the agent — does not grant the API key console access. Offer on long or sensitive tasks. Owner must be signed into Glasswarp; API keys alone cannot open the player. Required: session_id.
session.start(rig_id)
Start a metered desktop session on a USABLE rig from rigs.list. Side effects: begins wall-clock billing, shows an on-screen “API session active” indicator, enables observe/input until session.end. Idle sessions auto-end after ~15 minutes. Always call session.end when done or abandoning. Do not call if no USABLE rig exists. Returns session_id and Live View URL (owner console login required). Required: rig_id.
session.status(session_id)
Fetch session metadata: status, host, mode, created_at, action_count, billed_minutes. Read-only — no input side effects. Use to tell the user about metered time or confirm the session is still active before more actions. Required: session_id.

Last successful function declaration observed on . Source: https://mcp.glasswarp.com/mcp. We list what the server declared; we do not call any of these functions.

Endpoint status observed on . Source: https://mcp.glasswarp.com/mcp.

Signals

These are separate measurements of different things. They are deliberately not combined into one score, because a popularity number that mixes website traffic with saves and stars cannot be checked or acted on.

Signal Value What it measures Window Observed Source
GitHub stars 0 Number of GitHub accounts that bookmarked this repository since it was created. It is a bookmark count, not installs, not active users and not quality. cumulative, all time GitHub
Last commit 2026-08-01 Date of the most recent push to any branch. This is the strongest cheap indicator of whether the project is still maintained. point in time GitHub
Open issues 1 Open issues plus open pull requests, as GitHub counts them together. A high number can mean an active project or an abandoned one. as of fetch GitHub
Latest published version 0.1.0 Latest version string the maintainer published to the registry. as of fetch Model Context Protocol
Registry record last updated 2026-07-25 When the registry record was last updated by its maintainer. point in time Model Context Protocol
License Apache-2.0 Licence GitHub detected in the repository. Detection can be wrong; the LICENSE file is authoritative. as of fetch GitHub
First listed in the MCP Registry 2026-07-25 Date this server was first published to the official MCP Registry. Not a usage or quality measure. point in time Model Context Protocol
repository status active The repository exists on GitHub and is not archived. This says nothing about how recently it was worked on. as of fetch GitHub
mcp tools declared 16 tools Number of functions the server itself declared when asked to list them. This is what the server offers an agent, not a measure of how well any of them work. as of probe mcp.glasswarp.com
mcp endpoint status ok The server listed 16 functions when asked. as of probe mcp.glasswarp.com

Where to get it

Related, by what their authors tagged them

These share tags the maintainers applied themselves, such as computer-use, desktop-automation. Common tags like "mcp" or "ai" are ignored for this: agreeing with six hundred other projects is not a similarity.

This is not a recommendation and not a test result. It is a map of what the authors said their work is about.

How the author describes it

Topics the maintainer set on GitHub: ai-agents, computer-use, desktop-automation, mcp, windows-automation.

This record as data

Every field on this page, with its source and observation date, is in the catalog JSON. Fetch the whole kind at once instead of parsing this HTML.

GET /api/v1/entries/mcp_server.json

Sources

  1. glasswarp/mcp-server on GitHub — GitHub, observed , trust tier 3.
  2. Tools declared by the MCP server at https://mcp.glasswarp.com/mcp — mcp.glasswarp.com, observed , trust tier 1.
  3. Official MCP Registry — Model Context Protocol, observed , trust tier 1.