Skip to main content
Glama
Sign In
agy_computer_use.mcp_server

agy_computer_use.mcp_server

by orakulzero
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Python
Local

cu_ghost_desktop

Manages an isolated Win32 desktop session for automation that avoids focus theft, enabling window launching, enumeration, capture, and input dispatch without affecting the active desktop.

Instructions

Manage isolated Win32 kernel desktop session (WinSta0\AGY_GhostDesktop) for zero-focus-theft automation.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "action": "<action>"
    },
    "name": "cu_ghost_desktop"
  }
}

Input Schema

NameRequiredDescriptionDefault
hwndNoTarget window handle on ghost desktop.
textNoText to type or set.
actionYesGhost desktop action (create, launch, windows, enumerate, capture, dispatch, close).
norm_xNoX on [0..1000] grid.
norm_yNoY on [0..1000] grid.
dry_runNoSynthesize without OS dispatch.
wait_secNoSeconds to wait for window after launch.
drag_stepsNoIntermediate interpolation steps for drag.
end_norm_xNoEnd X on [0..1000] grid for drag.
end_norm_yNoEnd Y on [0..1000] grid for drag.
action_typeNoAction type for dispatch (click, type_text, etc.).
wheel_deltaNoScroll wheel delta.
command_lineNoCommand line to launch in isolated desktop.
desktop_nameNoDesktop session name (default 'AGY_GhostDesktop').
terminate_spawnedNoTerminate spawned processes on close.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv2.0.0

TDQS

C2.5/5.0
Behavior2/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations are provided, so the description must carry the full behavioral burden. The one-sentence description does not disclose side effects, permissions, process lifecycle, what close terminates, how dry_run behaves, or which actions mutate state.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness3/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single front-loaded sentence with no wasted text. However, it is too terse for a 15-parameter, 7-action tool and provides no structure around action categories or operational flow.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness2/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

This is a complex action-based tool with seven enum actions and 15 parameters, and no annotations or output schema. The description does not explain action semantics, lifecycle behavior, safety implications, or how to choose among actions, leaving significant gaps.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, so the schema already documents all 15 parameters, establishing a baseline of 3. The description adds little beyond confirming the default isolated desktop name and does not explain how parameters interact across actions.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose3/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description names a specific resource, an isolated Win32 desktop session, and a use case, zero-focus-theft automation. However, the verb 'Manage' is broad and the description does not clarify what the seven supported actions actually do or how this tool differs from siblings such as cu_bg_dispatch and cu_bg_capture.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines2/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The phrase 'for zero-focus-theft automation' gives a contextual hint, but there is no explicit guidance on when to use this tool instead of cu_bg_dispatch, cu_bg_capture, cu_click, or other siblings. It also omits prerequisites and when-not-to-use conditions.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Deploy Server

Other Tools