cua · job 75%filepilot_ai · job 71%mcp_pyautogui · job 74%clawdcursor · job 73%pharo_smalltalk_interop_mcp_se · job 73%AiPC · job 82%lmstudio_agent_mcp · job 74%Local Network MCP Server · job 72%Ganado Bridge · job 80%Free Coding Agent · job 75%jolink_runtime · job 76%Smalltalk Interop MCP Server · job 76%infrastructure_mcp · job 76%glass · job 75%Local MCP · job 74%computer_use_mcp · job 83%Pingo · job 79%tux_ai · job 78%local_coding_agent · job 78%imagesorcery_mcp · job 77%Health Monitor MCP · job 74%mcp_link · job 83%hypr_cua_mcp · job 77%mcp_kali_server · job 73%aioproductos_claude · job 71%desktop_commander_mcp · job 71%homelab_monitor · job 74%processhacker_mcp · job 73%airmcp · job 74%whats_running_mcp · job 71%basic_fns_mcp · job 76%synapse_2 · job 77%MCP · job 76%macOS Local MCP · job 75%execkit · job 73%Knowledge-MCP · job 73%Xiaozhi AI MCP Bridge · job 73%DeskTether · job 80%Linux MCP Daemon · job 78%ForgeBridge · job 72%Paddock · job 78%System Informer MCP · job 76%PC Bridge · job 75%GoreeCloud Remote MCP · job 75%zcode-desktop-control · job 78%MCP-MyPC · job 75%localhost-qa-mcp · 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