mcp · handle computer_use
trope_cua · job 79%open_codex_computer_use · job 78%glass · job 79%applescript_mcp · job 75%swift_mcp_gui · job 78%mcp_vnc · job 75%mcp_pyautogui · job 80%Sloth MCP · job 81%DSH Codex Computer Use · job 80%zcode-desktop-control · job 81%WinMind · job 82%Guarded Computer Use MCP · job 81%computer-control · job 77%Claude Background Control · job 82%OpenComputerUse · job 80%computer-use-linux · job 78%Waldo · job 78%macOS Local MCP · job 77%OpenSky · job 79%Ichiro · job 78%Windows Sandbox MCP · job 74%Emulator MCP · job 80%ScopeRail · job 79%macOS MCP Plugin · job 76%Dottie Mac Use · job 79%Conductor Desktop · job 79%Computer Use MCP · job 84%Computer MCP · job 80%DSH Computer Use · job 78%mac-reader · job 76%Auten · job 77%uitap · job 82%OS Control · job 76%dsh-cua · job 75%settled-computer · job 76%Sidehand · job 81%native-cua · job 80%AiPC · job 76%Luda · job 74%PcGöz · job 78%winmcp · job 76%touchpoint · job 84%desktop_pilot_mcp · job 77%plonk_2 · job 80%agentfenster · job 76%desktop-hub · job 83%Mac Developer Bridge · job 78%clawdcursor · job 78%Claude Codex Computer Use · job 77%Windows Computer Use MCP · job 77%mcp-hands · job 76%noxgild · 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