# Glasswarp (remote · mcp.glasswarp.com)

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

- Trust score: 77/100 (medium)
- Change this week: +56
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-08-04

## Components

- remote · `mcp.glasswarp.com`: 77/100 (this document), [markdown](https://verifymcp.io/servers/com-glasswarp-mcp-server/mcp.md), [page](https://verifymcp.io/servers/com-glasswarp-mcp-server/mcp)

## Channel facts

- Endpoint: `https://mcp.glasswarp.com/mcp`
- Transports: `streamable-http`
- Auth: `required`
- Version: `0.1.0`

## Trust breakdown

How this component scores in each security and reliability category. Every signal is checked automatically against the live server, and we only credit what we can confirm. Scores are 0–100 per category. Scoring method: https://verifymcp.io/docs/scoring (what has changed: https://verifymcp.io/docs/scoring/changelog)

Scored 2026-08-04.

- **Endpoint Security**: 83/100
  - The endpoint's TLS certificate is valid, in date, and uses a strong key.
  - Authorisation is enforced on tool calls, but the challenge carries no valid RFC 9728 metadata, so a client cannot discover where to get a token.
  - HTTPS is enforced; there's no plaintext access path.
  - HSTS check failed: the Strict-Transport-Security header is absent.
  - DNSSEC check failed: this domain isn't protected by DNSSEC.
- **Transport & Reachability**: 100/100
  - Verified streamable-http transport via a live MCP handshake.
- **Schema Quality & AI Usability**: 80/100
  - 100% of prompts and resources have a non-trivial description (not blank, and not just the item's name).
  - AI-judged instruction clarity (excellent).
  - Context-footprint check failed: tool/resource definitions use about 3503 tokens (~145/item across 24 items; 16 tools + 8 resources), over budget; trim descriptions and params.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 17/100
  - Stability observed for 5 of 30 days with no destabilising changes; credit accrues until the full window elapses.
- **Tool Coverage**: 100/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 100% of tool parameters carry a description.
  - Structured output schemas are declared (100% of tools); any adoption earns full credit.
- **Capabilities**: 100/100
  - Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.

## Install

### Claude

```bash
claude mcp add --transport http com-glasswarp-mcp-server https://mcp.glasswarp.com/mcp
```

### Codex

```toml
[mcp_servers.com-glasswarp-mcp-server]
url = "https://mcp.glasswarp.com/mcp"
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "com-glasswarp-mcp-server": {
      "type": "remote",
      "url": "https://mcp.glasswarp.com/mcp",
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add com-glasswarp-mcp-server --url https://mcp.glasswarp.com/mcp --transport streamable-http
```

### Hermes

```yaml
mcp_servers:
  com-glasswarp-mcp-server:
    url: "https://mcp.glasswarp.com/mcp"
```

### Other

```json
{
  "mcpServers": {
    "com-glasswarp-mcp-server": {
      "type": "http",
      "url": "https://mcp.glasswarp.com/mcp"
    }
  }
}
```

The mcpServers block is a cross-client convention. Remote transports vary, so check your client's docs.

## Changelog

Every change recorded for this component, newest first. Days that predate change tracking, or that we cannot explain, say so: "we were watching and nothing happened" and "we were not watching" are different claims.

### 2026-08-04 (score 77, +1)

No change was recorded against any check on this day. Stability & Change Management went from 13 to 17. That category is still filling its 30-day observation window: 4 days of observed history at the previous scan, 5 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-08-02 (score 76, +1)

No change was recorded against any check on this day. Stability & Change Management went from 7 to 10. That category is still filling its 30-day observation window: 2 days of observed history at the previous scan, 3 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-07-31 (score 75, +4)

- [functional] We updated how we score, so this day's move reflects our rubric, not a change to the server

### 2026-07-30 (score 71, +50)

- [functional] We updated how we score, so this day's move reflects our rubric, not a change to the server

### 2026-07-27 (score 21, 0)

- [functional] We updated how we score, so this day's move reflects our rubric, not a change to the server

### 2026-07-26 (score 21)

First indexed and scored.

## MCP tools (16)

### `demos.list` (~105 tokens)

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 parameters:

- `format` (string): Response format: markdown (default) or json

Output parameters:

- `message` (string): Human-readable result for the agent
- `ok` (boolean): False when the tool failed

### `demos.get` (~105 tokens)

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.

Input parameters:

- `demo_id` (string, required): Showcase id from demos.list
- `format` (string): Response format: markdown (default) or json

Output parameters:

- `message` (string): Human-readable result for the agent
- `ok` (boolean): False when the tool failed

### `rigs.list` (~99 tokens)

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.

Output parameters:

- `message` (string): Human-readable result for the agent
- `ok` (boolean): False when the tool failed

### `session.start` (~111 tokens)

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).

Input parameters:

- `rig_id` (string, required): Rig id from rigs.list (must be online with api_access_enabled)

Output parameters:

- `message` (string): Human-readable result for the agent
- `ok` (boolean): False when the tool failed

### `session.end` (~73 tokens)

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.

Input parameters:

- `session_id` (string, required): Session id returned by session.start

Output parameters:

- `message` (string): Human-readable result for the agent
- `ok` (boolean): False when the tool failed

### `screen.observe` (~235 tokens)

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.

Input parameters:

- `image` (boolean): Include JPEG (default false). True only to visually read/judge the screen.
- `mark` (boolean): Overlay numbered targets on JPEG when image=true (default true; ignored if image=false)
- `max_width` (integer): JPEG max width when image=true (default 960). Clicks always use native coords, not JPEG pixels.
- `quality` (integer): JPEG quality 40–100 when image=true (default 60)
- `session_id` (string, required): Active session id from session.start

Output parameters:

- `changed`: Whether the frame changed since last observe; null if unknown
- `has_image` (boolean): True when a JPEG was included in the MCP content
- `message` (string): Human-readable observe summary / targets
- `native_height` (integer): Native capture height
- `native_width` (integer): Native capture width
- `ok` (boolean): False when the tool failed

### `input.click_target` (~150 tokens)

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.

Input parameters:

- `button` (string): Mouse button (default left)
- `double` (boolean): If true, double-click (two clicks)
- `session_id` (string, required): Active session id
- `target_id` (string, required): Target id from the most recent screen.observe (e.g. uia-… )

Output parameters:

- `message` (string): Human-readable result for the agent
- `ok` (boolean): False when the tool failed

### `input.click_xy` (~134 tokens)

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.

Input parameters:

- `button` (string): Mouse button (default left)
- `double` (boolean): If true, double-click
- `session_id` (string, required): Active session id
- `x` (integer, required): Native X (0…native_width-1)
- `y` (integer, required): Native Y (0…native_height-1)

Output parameters:

- `message` (string): Human-readable result for the agent
- `ok` (boolean): False when the tool failed

### `input.type_text` (~100 tokens)

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.

Input parameters:

- `session_id` (string, required): Active session id
- `text` (string, required): Literal text to type (not a key combo)

Output parameters:

- `message` (string): Human-readable result for the agent
- `ok` (boolean): False when the tool failed

### `input.send_keys` (~117 tokens)

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.

Input parameters:

- `keys` (string, required): Key or combo, e.g. enter, tab, ctrl+s, alt+f4, win
- `session_id` (string, required): Active session id

Output parameters:

- `message` (string): Human-readable result for the agent
- `ok` (boolean): False when the tool failed

### `input.drag` (~141 tokens)

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.

Input parameters:

- `duration_ms` (integer): Approx drag duration in ms; more steps when larger (default ~200)
- `from_x` (integer, required): Native start X
- `from_y` (integer, required): Native start Y
- `session_id` (string, required): Active session id
- `to_x` (integer, required): Native end X
- `to_y` (integer, required): Native end Y

Output parameters:

- `message` (string): Human-readable result for the agent
- `ok` (boolean): False when the tool failed

### `input.scroll` (~126 tokens)

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.

Input parameters:

- `delta` (integer, required): Vertical wheel delta (negative = toward bottom of page)
- `session_id` (string, required): Active session id
- `x` (integer, required): Native X to hover before scrolling
- `y` (integer, required): Native Y to hover before scrolling

Output parameters:

- `message` (string): Human-readable result for the agent
- `ok` (boolean): False when the tool failed

### `input.send_actions` (~200 tokens)

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.

Input parameters:

- `actions` (array, required): Ordered actions (max 10); input.click_target needs target_id from latest screen.observe
- `observe_after` (boolean): Default true. When true, return a verification observe in the same result
- `observe_image` (boolean): Default false. When true with observe_after, include verification JPEG unless changed=false
- `session_id` (string, required): Active session id

Output parameters:

- `changed`: Whether the frame changed since last observe; null if unknown
- `has_image` (boolean): True when a JPEG was included in the MCP content
- `message` (string): Human-readable observe summary / targets
- `native_height` (integer): Native capture height
- `native_width` (integer): Native capture width
- `ok` (boolean): False when the tool failed

### `app.launch` (~138 tokens)

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.

Input parameters:

- `args` (array): Process args, e.g. ["--new-window", "https://example.com"]
- `path_or_name` (string, required): Executable name (e.g. notepad.exe) or absolute path
- `session_id` (string, required): Active session id

Output parameters:

- `message` (string): Human-readable result for the agent
- `ok` (boolean): False when the tool failed

### `session.live_view` (~78 tokens)

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.

Input parameters:

- `session_id` (string, required): Active session id

Output parameters:

- `message` (string): Human-readable result for the agent
- `ok` (boolean): False when the tool failed

### `session.status` (~68 tokens)

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.

Input parameters:

- `session_id` (string, required): Session id from session.start

Output parameters:

- `message` (string): Human-readable result for the agent
- `ok` (boolean): False when the tool failed

## Diagnostics

Captured diagnostic sections: TLS, DNSSEC, Authorisation, Transports. The full working is on the page: https://verifymcp.io/servers/com-glasswarp-mcp-server/mcp#diagnostics

## Score history

- 2026-08-04: 77
- 2026-08-03: 76
- 2026-08-02: 76
- 2026-08-01: 75
- 2026-07-31: 75
- 2026-07-30: 71
- 2026-07-29: 21
- 2026-07-28: 21
- 2026-07-27: 21
- 2026-07-26: 21

## Links

- Remote endpoint: https://mcp.glasswarp.com/mcp
- Authorisation metadata: https://mcp.glasswarp.com/.well-known/oauth-protected-resource/mcp
- Repository: https://github.com/glasswarp/mcp-server
- Website: https://www.glasswarp.com/mcp
- Changelog RSS feed: https://verifymcp.io/servers/com-glasswarp-mcp-server/mcp/changelog.xml
- Changelog JSON feed: https://verifymcp.io/servers/com-glasswarp-mcp-server/mcp/changelog.json
- HTML version of this page: https://verifymcp.io/servers/com-glasswarp-mcp-server/mcp