mcp · handle pc_screen_control_2
desktop_commander_mcp_2 · job 80%browser_mcp · job 74%applescript_mcp · job 71%mcp_pyautogui · job 80%safari_mcp_server · job 73%touchpoint · job 83%mcp_link · job 74%glass · job 74%computer_use_mcp · job 78%pc_screen_control · job 87%freya_mcp_server · job 79%mcp_aoai_web_browsing · job 76%multicad_mcp · job 71%clawdcursor · job 79%open_codex_computer_use · job 78%auto_browser · job 72%win_cli_mcp_server · job 75%trope_cua · job 81%hypruse · job 77%hypr_cua_mcp · job 78%xamlmcp · job 75%agentfenster · job 73%opencode GUI Bridge · job 86%Little Mouse Pointer · job 82%uiinspect_mcp · job 80%aos · job 78%glasswarp_mcp_server · job 74%SoftAuto · job 80%Hyprland MCP · job 78%Custom AI View · job 76%System Informer MCP · job 74%lnwjud-readme · job 76%Filesystem MCP Server · job 74%PwshDeck · job 79%Terminal Server · job 77%Desktop Automation MCP · job 74%MonitorControl · job 78%CLIP STUDIO PAINT 5.1.2 Production MCP · job 73%wavn · job 75%haden-browser · job 74%DesktopVisionMCP · job 74%uisight · job 73%byob · job 73%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