广告合作
MCP.so
登录

Glasswarp MCP Server已验证已精选

@Glasswarp

代码仓库主页文档

基本信息

分类

其他

许可证

Apache-2.0

作者

Glasswarp

提交者

saferelay

关于 Glasswarp MCP Server

See and control a real Windows PC you own — from any MCP client, locally or remotely. Observe (UIA + screenshots), click/type/drag/scroll, launch apps, owner Live View. BYOH: your machine, your key.

#Desktop Automation

Glasswarp MCP Server 配置

使用下面的配置,将此服务器添加到你的 MCP 客户端。

{
  "mcpServers": {
    "glasswarp": {
      "command": "npx",
      "args": [
        "-y",
        "@glasswarp/mcp"
      ],
      "env": {
        "GLASSWARP_API_KEY": "gw_live_sk_REPLACE_WITH_YOUR_KEY"
      }
    }
  }
}

Glasswarp MCP Server 工具

16

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.

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.

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.

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).

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 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.

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.

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.

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.

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.

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.

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.

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.

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.

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.

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.

概览

What is Glasswarp?

Glasswarp gives AI agents eyes and hands on a real Windows PC you own (BYOH). Hosted MCP or local npx @glasswarp/mcp — the agent runs anywhere; the PC stays yours. You bring the model (the brain).

  • Observe: UIA targets + optional screenshots
  • Act: click, type, keys, drag, scroll, batched input.send_actions
  • Launch apps, owner Live View, consent + kill switch + audit

Remote URL: https://mcp.glasswarp.com/mcp
Stdio: npx -y @glasswarp/mcp

How to use Glasswarp?

  1. Install the Windows host, pair the rig, enable API access
  2. Create an API key at console
  3. Add MCP config (Config tab) or point a remote client at https://mcp.glasswarp.com/mcp with Authorization: Bearer gw_…
  4. Flow: rigs.list → session.start → screen.observe → act → session.end

Docs: Connect via MCP

Key features

  • Local or remote MCP (not on-box-only)
  • UIA grounding + native input on real Windows
  • Owner Live View, visible session indicator, kill switch
  • Official registry: com.glasswarp/mcp-server
  • Open source server: Apache-2.0

Use cases

  • Computer-use agents on real Windows apps (not a cloud VM)
  • QA / regression on licensed desktop software
  • Remote GPU workstation control from Cursor / Claude

常见问题

1

Do I need a Windows PC?

Yes. Glasswarp is BYOH — you pair your own machine. We don’t host the desktop.

2

Is this the same as local-only desktop MCPs?

No. Those only control the machine where MCP runs. Glasswarp works from any client against a paired Windows rig.

3

Where’s the source?

https://github.com/glasswarp/mcp-server

评论

其他 分类下的更多 MCP 服务器

FastMCP v2 🚀

jlowin

🚀 The fast, Pythonic way to build MCP servers and clients.

26.0K

Lemon.io

lemon-io

Request dedicated senior developers to work on your project, write job descriptions, and prep technical interviews — all without leaving your Claude chat. Just describe what you need, and Lemon.io MCP does the rest. 1–3

Reactive Resume

amruthpillai

A one-of-a-kind resume builder that keeps your privacy in mind. Completely secure, customizable, portable, open-source and free forever. Try it out today!

39.5K

DeepMark

DeepMark helps teachers deliver rapid, consistent marking with meaningful feedback for every student — in a fraction of the time. What once took a week, now takes one free period.

MCP Toolbox for Databases

googleapis

MCP Toolbox for Databases is an open source MCP server for databases.

15.9K
广告合作