mcp · handle mac_developer_bridge
agentic_terminal_mcp_sayani · job 76%airmcp · job 80%hunch · job 75%applescript_mcp · job 77%gantry · job 72%piloty · job 73%taskflow_ai · job 74%Claude Codex Computer Use · job 76%termmirror · job 71%mcp-tty · job 71%Sloth MCP · job 78%VT-AIAgent · job 71%macOS Local MCP · job 78%Computer Use · job 78%Phosphor · job 72%Moonlight MCP Plugin · job 77%bcd · job 76%Agent MCP · job 74%RAT · job 73%native-cua · job 77%Claude Background Control · job 78%aos · job 78%Computer MCP · job 78%OpenCode Connect · job 73%VerityMCP · job 72%macOS MCP Plugin · job 74%Cider · job 78%termcp · job 75%Warp Command Runner · job 81%ScopeRail · job 81%FileMCP · job 77%Codex Bridge · job 74%OS Control · job 76%Computer MCP · job 73%pty_mcp_server · job 72%docker_mcp_chatgpt · job 73%chatgpt2localbridge · job 75%agentbridge · job 78%plonk_2 · job 74%mcp_interactive_terminal · job 74%desktop_pilot_mcp · job 77%interactive_terminal_mcp · job 73%macuse · job 77%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