mcp · handle mac_reader
swift_mcp_gui · job 79%ScopeRail · job 76%hypr_cua_mcp · job 71%desktop-hub · job 79%macos_mcp · job 80%hop · job 72%native-cua · job 82%agentbridge · job 75%plonk_2 · job 76%macOS Local MCP · job 80%Terminal Server · job 75%aos · job 81%gantry · job 74%Computer MCP · job 75%macuse · job 75%mcp_vnc · job 77%trope_cua · job 76%cmux-mcp · job 78%shortcuts_mcp_server · job 72%FlashDesk MCP · job 74%airmcp · job 80%FileMCP · job 74%ssh_mcp_server · job 78%xojo-mcp · job 74%applescript_mcp · job 77%mcp_ssh_connectors · job 74%SshWarden · job 76%clawdcursor · job 74%macOS MCP Server · job 78%Computer Use MCP · job 81%desktop_pilot_mcp · job 76%Sloth MCP · job 77%Computer Use · job 76%open_codex_computer_use · job 81%Dottie Mac Use · job 80%touchpoint · job 80%iOS Control MCP · job 73%Claude Background Control · job 79%AiPC · job 77%bcd · job 79%tussh · job 77%2native SSH MCP · job 74%OS Control · job 78%MCP Server SSH · job 76%uitap · job 80%Claude Codex Computer Use · job 72%Longarm MCP · job 76%Warp Command Runner · job 81%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