mcp · handle dsh_computer_use · source page
clawdcursor · job 80%plonk_2 · job 76%hypruse · job 77%Computer Use MCP · job 80%MCP Computer Use · job 74%Sloth MCP · job 76%Computer Use · job 78%glasswarp_mcp_server · job 79%Multi-UIAutomator2 · job 75%Guarded Computer Use MCP · job 80%mcp_link · job 76%swift_mcp_gui · job 77%DeepSeek Vision MCP · job 78%mcp_pyautogui · job 79%miniscreenshot · job 75%PcGöz · job 77%Deskhand MCP · job 79%Flash Computer Use · job 82%Behead Browser MCP · job 82%Muse Link · job 75%OpenSky · job 76%TarsUITarsBridge · job 77%dsh-cua · job 76%zcode-desktop-control · job 76%Anode · job 76%Windows-Use MCP · job 80%uitap · job 79%cmux-mcp · job 77%Tiance GUI MCP · job 85%nuphus_mcp · job 80%Hyprland MCP · job 78%touchpoint · job 76%LocalHands · job 74%agentfenster · job 82%hypr_cua_mcp · job 76%desktop-hub · job 77%desktop_commander · job 74%deepseek_vision_mcp_2 · job 78%Desktop Automation MCP · job 79%ControlFreak · job 76%WinMind · job 79%computer-control · job 78%dsh-ops-mcp · job 83%OpenComputerUse · job 81%computer-use-linux · job 80%ORVEX · job 79%Luda · job 76%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