mcp · handle sideyard
desktop_commander · job 78%mcp_link · job 78%basic_fns_mcp · job 78%LocalHands · job 79%ControlFreak · job 83%Kobel · job 81%mcp_router · job 84%mcp_frontend · job 78%ipybox · job 79%aos · job 82%GenPark · job 82%claude_kvm · job 77%system-command-mcp · job 80%lnwjud-readme · job 79%AI Commander · job 81%open_codex_computer_use · job 82%RemoteManager MCP · job 81%Rob Desktop Commander · job 85%mcp_pyautogui · job 78%ChatGPT Desktop MCP · job 77%smart_terminal_mcp · job 81%autonomo_mcp · job 78%nuphus_mcp · job 80%mandala · job 86%KeyAI PC Commander · job 80%MCP Bridge · job 78%Windows Local MCP · job 85%Desktop Bridge · job 81%Ganado Bridge · job 81%Luda · job 81%AiPC · job 80%FullRemote MCP · job 79%computer-use-linux · job 84%local-mcp · job 80%remcp · job 80%lurq · job 79%ORVEX · job 78%hwcast · job 78%MCP Node Zig · job 82%computer-control · job 83%Fishbowl · job 83%Universal AI Bridge · job 85%Local Terminal MCP · job 80%zcode-desktop-control · job 78%mcp-local-telemetry · job 83%AirSCP · job 79%ZCode for Chrome · job 79%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