mcp · handle mcp_computer_use · source page
kwin_mcp · job 75%Mint Computer MCP · job 75%Desktop Automation MCP · job 77%agentfenster · job 75%desktop-hub · job 78%Hyprland MCP · job 76%touchpoint · job 76%Sloth MCP · job 75%hypruse · job 79%Computer Use MCP · job 79%wayhand-mcp · job 71%Windows-Use MCP · job 78%WinMind · job 77%computer-use-linux · job 79%use-computer · job 78%UltraNix MCP · job 77%OpenComputerUse · job 77%Claude Background Control · job 76%mcp_pyautogui · job 78%rdc · job 77%uiinspect_mcp · job 71%plonk_2 · job 80%hypr_cua_mcp · job 75%Guarded Computer Use MCP · job 80%mcp_vnc · job 77%PcGöz · job 77%Hypr Computer · job 75%winmcp · job 75%kasm-use · job 73%mcp-winaccess-win · job 78%settled-computer · job 71%libtmux-mcp · job 77%cc-computer-use · job 78%UI-Venus MCP · job 76%uitap · job 84%Game Player MCP · job 74%Tiance GUI MCP · job 79%Luda · job 81%FullRemote MCP · job 78%DSH Computer Use · job 74%Anode · job 78%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