mcp · handle computer_use_linux
mcp_pyautogui · job 80%ChatGPT Desktop MCP · job 77%rdc · job 76%OpenSky · job 82%ControlFreak · job 80%opencode GUI Bridge · job 77%DSH Computer Use · job 80%Muse Link · job 76%Sideyard · job 84%Desktop Automation MCP · job 81%cc-computer-use · job 82%agentfenster · job 76%touchpoint · job 80%computer-control · job 83%nuphus_mcp · job 85%cmux-mcp · job 78%pc_screen_control_2 · job 77%UltraNix MCP · job 83%use-computer · job 80%Claude Background Control · job 77%MCP Computer Use · job 79%Xenon Browser · job 77%clawdcursor · job 76%plonk_2 · job 77%mandala · job 87%GoreeCloud Remote MCP · job 76%PcGöz · job 82%Hypr Computer · job 78%Auten · job 76%AiPC · job 79%FullRemote MCP · job 76%OpenComputerUse · job 79%Fishbowl · job 83%Luda · job 89%Mint Computer MCP · job 83%dsh-cua · job 78%screenhand · job 78%swift_mcp_gui · job 79%Guarded Computer Use MCP · job 81%WinMind · job 79%open_codex_computer_use · job 81%glasswarp_mcp_server · job 78%Hyprland MCP · job 79%Tiance GUI MCP · job 80%Computer Use · job 78%uitap · job 78%aos · job 82%wayhand-mcp · job 77%hypruse · job 80%Computer Use MCP · job 80%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