mcp · handle computer_use
nuphus_mcp · job 78%open_codex_computer_use · job 78%openowl · job 75%pc_screen_control · job 73%pc_screen_control_2 · job 74%plonk_2 · job 80%plonk · job 78%Remarc · job 76%safari_mcp_server · job 72%swift_mcp_gui · job 78%touchpoint · job 84%trope_cua · job 79%webclaw_2 · job 74%win_cli_mcp_server · job 72%Rei Automator MCP · job 72%airmcp · job 77%aos · job 77%applescript_mcp · job 75%byob · job 74%Chrome Actuator · job 71%Browser Tools MCP · job 74%Hyprland MCP · job 73%hypruse · job 72%clawdcursor · job 78%Mac Developer Bridge · job 78%macos_mcp · job 76%desktop_pilot_mcp · job 77%mcp_osascript · job 74%mcp_pyautogui · job 80%mcp_vnc · job 75%Custom AI View · job 73%Desktop Automation MCP · job 74%desktop-hub · job 83%humanized_browser · job 74%agentfenster · job 76%ChromeBoost · job 75%browser_bridge_2 · job 72%glass · job 79%hunch · job 74%mobile_mcp · job 70%Little Mouse Pointer · job 71%flowlens_mcp_server · job 74%mcp_browser_agent · job 72%mcp_link · job 75%mcp_pointer · job 72%mcp-stama · job 76%Annote · job 75%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