{"id":"com.glasswarp/mcp-server","slug":"com-glasswarp-mcp-server","title":"Glasswarp","description":"Eyes and hands on real Windows PCs — observe, click, type via Glasswarp API.","version":"0.1.0","publisher":{"kind":"domain","id":"glasswarp.com","label":"glasswarp.com","url":"https://glasswarp.com"},"website":"https://www.glasswarp.com/mcp","repository":"https://github.com/glasswarp/mcp-server","remotes":[{"type":"streamable-http","url":"https://mcp.glasswarp.com/mcp","headers":[{"description":"Bearer Glasswarp API key (gw_…). Create one at https://www.glasswarp.com/console → API Keys.","isRequired":true,"format":"string","isSecret":true,"name":"Authorization"}]}],"packages":[],"published":"2026-07-25","updated":"2026-07-25","status":"online","auth":"","latency_ms":925,"checked":"2026-11-19","uptime":100,"checks":3,"tools":[{"name":"demos.list","title":"","description":"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.","read_only":true},{"name":"demos.get","title":"","description":"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.","read_only":true},{"name":"rigs.list","title":"","description":"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.","read_only":true},{"name":"session.start","title":"","description":"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).","read_only":false},{"name":"session.end","title":"","description":"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.","read_only":false},{"name":"screen.observe","title":"","description":"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","read_only":true},{"name":"input.click_target","title":"","description":"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.","read_only":false},{"name":"input.click_xy","title":"","description":"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.","read_only":false},{"name":"input.type_text","title":"","description":"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.","read_only":false},{"name":"input.send_keys","title":"","description":"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.","read_only":false},{"name":"input.drag","title":"","description":"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.","read_only":false},{"name":"input.scroll","title":"","description":"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.","read_only":false},{"name":"input.send_actions","title":"","description":"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 unp","read_only":false},{"name":"app.launch","title":"","description":"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.","read_only":false},{"name":"session.live_view","title":"","description":"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.","read_only":true},{"name":"session.status","title":"","description":"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.","read_only":true}],"server_info":{"name":"glasswarp","version":"0.1.0","title":"Glasswarp","description":"Eyes and hands on real Windows PCs you own. You bring the brain. Short tasks → MCP tools; longer tasks → offer scaffold when the client can run code (never impose). Prompts: best_practices, demo_minesweeper, demo_mona_lisa.","websiteUrl":"https://docs.glasswarp.com/guides/ways-to-run-agents"},"category":"other","tags":[],"kind":"remote","source":"registry","submitted":{},"first_party":true,"domain_rank":null,"score":100,"indexable":true,"first_seen":"2026-07-25","stars":0,"badges":[],"sponsor":null,"page":"https://agentsindex.org/agents/com-glasswarp-mcp-server/"}