mcp · handle uisight
sncro · job 78%visionaire_engine · job 79%touchpoint · job 78%vibetest_mcp · job 73%vynix · job 85%waydroid_mcp · job 71%Brave DevTools MCP · job 71%autonomo_mcp · job 77%manifest · job 73%browser_mcp · job 76%BunBrowser MCP · job 75%EagleEye MCP · job 76%Cognitive Browser · job 75%glance · job 75%js_reverse_mcp · job 73%webscore · job 74%clamp_analytics · job 74%limitlessmarketingfj_standout · job 82%android_ui_mcp · job 76%luciq · job 74%drissionpage_mcp_server · job 76%Kroma MCP · job 74%AI Web Tester · job 79%mcp_pyautogui · job 76%mobile_mcp · job 72%Mimiq · job 84%safari_mcp_server · job 76%mcp_screenshot_server · job 74%pc_screen_control · job 74%pc_screen_control_2 · job 73%glass · job 76%clawdcursor · job 76%raven_mcp · job 80%browser_bridge · job 73%Custom AI View · job 83%frontend-eyes · job 81%web_intelligence · job 75%opencode GUI Bridge · job 73%designlang · job 73%Chrome DevTools MCP · job 75%Little Mouse Pointer · job 74%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