Digitomancy · job 81%MobileMCP · job 76%droid_mcp · job 76%mcp_android_server · job 70%Oh My Android · job 79%DroidLume Agent Control · job 72%scrcpy_mcp · job 77%jevdevice · job 88%android_mcp · job 87%waydroid_mcp · job 81%Multi-UIAutomator2 · job 80%DroidBridge · job 78%Android Root MCP · job 74%agent_droid_bridge · job 74%Agent Phone Harness · job 76%Auto Phone · job 79%Phone for AI · job 77%phone-mcp · job 79%Gemini Spark MCP Bridge · job 71%Android MCP · job 72%android-adb-mcp · job 81%android_remote_control_mcp · job 74%adbfriend · job 73%Mobilerun MCP · job 84%Android Use · job 82%Mobile App Testing AI Agent MCP Server · job 80%Android-MCP-go · job 75%AutoMobile · job 75%android-lite · job 79%Codex Android Control · job 76%neuralbridge · job 76%Karagöz · job 79%rc-mcp · job 70%screenpilot · job 78%deepadb · job 75%ARTEMIS Harness · job 73%interactive_mcp · job 71%screenhand · job 75%Android Autopilot MCP · job 84%Android ADB MCP Server · job 80%android-mcp · job 76%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