mcp · handle swift_mcp_gui
airmcp · job 84%desktop_pilot_mcp · job 77%shortcuts_mcp · job 74%shortcuts_mcp_server · job 74%mcp_pyautogui · job 77%touchpoint · job 76%idb_mcp · job 73%autonomo_mcp · job 78%macuse · job 76%mcp_osascript · job 77%screenpilot · job 71%Axint · job 76%screenhand · job 74%aos · job 84%macos_mcp · job 85%macOS MCP Server · job 84%nuphus_mcp · job 80%desktop-hub · job 82%Cupertino · job 83%plonk_2 · job 79%glasswarp_mcp_server · job 78%opencode GUI Bridge · job 77%applescript_mcp · job 78%xamlmcp · job 76%plonk · job 80%computer_use_mcp · job 74%open_codex_computer_use · job 77%waydroid_mcp · job 75%Desktop Automation MCP · job 76%humanized_browser · job 75%agentfenster · job 76%rPlay SDK · job 72%Moonlight MCP Plugin · job 75%glass · job 74%hypruse · job 72%ChatGPT Desktop MCP · job 72%clawdcursor · job 74%mobile_mcp · job 72%ruyi_mcp · job 74%hunch · job 71%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