mcp · handle dsh_game_control
UltraNix MCP · job 72%use-computer · job 70%Claude Background Control · job 73%OpenComputerUse · job 76%Computer Use MCP · job 79%MCP Computer Use · job 75%settled-computer · job 70%mcp-winaccess-win · job 82%Hyprland MCP · job 72%Guarded Computer Use MCP · job 80%computer-control · job 78%WinMind · job 78%Ganglion · job 80%screenpilot · job 71%LovePilot · job 70%cc-computer-use · job 71%UI-Venus MCP · job 74%dsh-cua · job 75%Little Mouse Pointer · job 75%Deskhand MCP · job 80%Window Pilot · job 82%San9MCP · job 70%vway · job 71%uitap · job 76%Desktop Automation MCP · job 82%pc_screen_control · job 75%kasm-use · job 77%Windows-Use MCP · job 82%Windows Computer Use MCP · job 82%Anode · job 77%FullRemote MCP · job 78%Xbox AI Controller · job 71%playnice · job 74%mcp_pyautogui · job 78%OpenSky · job 81%uiinspect_mcp · job 72%layershot · job 77%ControlFreak · job 78%hypruse · job 74%win-mcp-bridge · job 76%Tiance GUI MCP · job 82%Overshoulder · job 80%mcp_vnc · job 71%Game Player MCP · job 89%PcGöz · job 81%opencode GUI Bridge · job 76%Sidehand · job 80%native-cua · job 72%Percentages are graph-similarity metadata, not suitability scores. A graph edge answers “is it connected” — plan fit and comparable cost are checked below.
Pick the exact reference and alternative series. Each history is separate; gaps stay gaps.
This view calls the same get_evidence tool your agent would — chart, table and MCP response describe the same records. Watch the reference series