mcp · handle softauto
mcp_pyautogui · job 80%nodriver_mcp_server · job 80%clawdcursor · job 80%mcp_link · job 79%opencode GUI Bridge · job 81%browseros · job 73%pydoll_mcp · job 75%pilot_mcp · job 77%mcp_browser_agent · job 74%ai_browser_mcp · job 83%safari_mcp_server · job 75%openowl · job 74%drissionpage_mcp · job 78%pc_screen_control · job 84%pc_screen_control_2 · job 80%pilotbrowsemcp · job 79%uiinspect_mcp · job 80%Rei Automator MCP · job 73%AgentSmith · job 74%Desktop Automation MCP · job 76%desktop-hub · job 76%mcp_pointer · job 76%touchpoint · job 81%Brave DevTools MCP · job 74%browser_mcp · job 77%trope_cua · job 79%freya_mcp_server · job 78%glance · job 77%glasswarp_mcp_server · job 73%Little Mouse Pointer · job 84%drissionpage_mcp_server · job 80%agentfenster · job 73%Custom AI View · 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