open_codex_computer_use · job 84%stealth_browser_mcp · job 81%agentos_ai · job 80%trope_cua · job 79%nuphus_mcp · job 81%mcp_frontend · job 82%glass · job 81%mcp_pyautogui · job 80%Nexus Browser MCP · job 84%macos_mcp · job 80%mcp_link · job 79%x402nano · job 83%airmcp · job 80%mu · job 88%ORVEX · job 85%aos · job 83%Computer Use MCP · job 81%browser_use_mcp · job 84%autonomo_mcp · job 85%touchpoint · job 80%cloakbrowser_mcp · job 82%browsermcp · job 82%mcp_web · job 85%Confident Christmasfactor 2015 MCP Server · job 81%mandala · job 84%Browser Agents MCP · job 83%Behead Browser MCP · job 82%Hermes Web MCP · job 81%ZCode for Chrome · job 81%AI Tool MCP Server · job 84%neu-browser-mcp · job 82%TeleDOM · job 82%Flash Computer Use · job 87%Deskhand MCP · job 87%Vmotif · job 83%Browser MCP · job 83%MCP Browser Use · job 81%Sideyard · job 82%mcp-web · job 86%Fishbowl · job 84%Orvima · 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