mcp · handle clawdcursor
trope_cua · job 80%browser_mcp · job 73%allcanuse_mcp · job 73%autonomo_mcp · job 78%touchpoint · job 88%mcp_pyautogui · job 85%mcp_link · job 77%desktop_pilot_mcp · job 71%swift_mcp_gui · job 74%airmcp · job 75%drissionpage_mcp_server · job 74%openowl · job 71%open_codex_computer_use · job 77%glasswarp_mcp_server · job 72%pc_screen_control_2 · job 79%agent_browser_mcp · job 73%pc_screen_control · job 82%uiinspect_mcp · job 80%plonk · job 76%plonk_2 · job 75%humanized_browser · job 74%computer_use_mcp · job 77%xamlmcp · job 72%Little Mouse Pointer · job 80%desktop-hub · job 78%SoftAuto · job 80%opencode GUI Bridge · job 77%agentfenster · job 74%glass · job 75%Desktop Automation MCP · job 75%uisight · job 76%hypr_cua_mcp · job 75%Hyprland MCP · job 77%Custom AI View · job 76%hypruse · job 76%System Informer MCP · 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