mcp · handle phone_for_ai
Multi-UIAutomator2 · job 78%android-mcp · job 76%Android ADB MCP Server · job 83%airi_android · job 77%Gemini Spark MCP Bridge · job 74%agent_droid_bridge · job 79%rPlay SDK · job 74%neuralbridge · job 78%mcp_android_server · job 73%Susu Phone Agent · job 73%Android Autopilot MCP · job 82%React Native MCP · job 70%waydroid_mcp · job 78%Android-MCP-go · job 81%AutoMobile · job 79%screenhand · job 78%textbee MCP Server · job 72%mobilenext_mcp · job 77%scrcpy_mcp · job 84%ADB MCP Server · job 71%deepadb · job 80%android_remote_control_mcp · job 86%melaya · job 78%Auto Phone · job 81%mcp-hands · job 77%Mobilerun MCP · job 84%Android Use · job 80%android-lite · job 83%webadb-agent · job 80%Codex Android Control · job 78%Karagöz · job 80%ARTEMIS Harness · job 76%DroidBridge · job 90%jevdevice · job 73%iOS Control MCP · job 73%Agent Phone Harness · job 82%PyPhone MCP Server · job 77%MobileMCP · job 85%Oh My Android · job 83%aCelery · job 75%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