mcp · handle os_control
trope_cua · job 81%macuse · job 80%mcp_osascript · job 75%Dottie Mac Use · job 73%NexusOS Semantic · job 72%Claude Background Control · job 86%aos · job 80%Sloth MCP · job 83%applescript_mcp · job 80%native-cua · job 84%DesktopVisionMCP · job 76%clawdcursor · job 79%agentbridge · job 76%uiinspect_mcp · job 73%hunch · job 72%Claude Codex Computer Use · job 77%OpenSky · job 79%desktop-hub · job 76%dsh-cua · job 76%apple-cloud-mcp · job 72%swift_mcp_gui · job 79%ScopeRail · job 76%bcd · job 75%Mac Developer Bridge · job 76%cc-computer-use · job 72%PcGöz · job 78%pc_screen_control_2 · job 79%Computer Use · job 76%uitap · job 83%touchpoint · job 81%WinMind · job 78%open_codex_computer_use · job 78%Hyprland MCP · job 72%desktop_pilot_mcp · job 83%Computer Use MCP · job 78%macOS Local MCP · job 80%Little Mouse Pointer · job 72%Computer MCP · job 76%OpenComputerUse · job 80%AppWrangler · job 71%mac-reader · job 78%plonk_2 · job 76%airmcp · job 80%xamlmcp · job 73%pc_screen_control · job 77%zcode-desktop-control · job 73%UI-Venus MCP · job 77%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