mcp · handle desktop_automation_mcp
openowl · job 73%swift_mcp_gui · job 76%xamlmcp · job 74%plonk_2 · job 76%clawdcursor · job 75%touchpoint · job 75%uiinspect_mcp · job 76%humanized_browser · job 74%glasswarp_mcp_server · job 83%Hyprland MCP · job 72%mcp_pyautogui · job 80%app_screenshot_mcp · job 75%nuphus_mcp · job 79%screenpilot · job 76%DeepSeek Vision MCP · job 72%mobile_mcp · job 71%pc_screen_control_2 · job 74%computer_use_mcp · job 71%agentfenster · job 79%Rei Automator MCP · job 77%Custom AI View · job 78%wayhand-mcp · job 73%EagleEye MCP · job 84%Little Mouse Pointer · job 79%Computer Use · job 74%pc_screen_control · job 76%hypr_cua_mcp · job 73%hypruse · job 73%desktop-hub · job 76%OmniParser MCP · job 73%opencode GUI Bridge · job 80%native-cua · job 73%System Informer MCP · job 71%SoftAuto · 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