mcp · handle phone_mcp
neuralbridge · job 81%android-lite · job 89%webadb-agent · job 77%Codex Android Control · job 76%agent_droid_bridge · job 82%mcp_android_server · job 76%Flownato MCP · job 71%Agent Phone Harness · job 82%MobileMCP · job 83%DroidLens · job 74%adbfriend · job 75%Phone Chrome MCP · job 80%melaya · job 78%mobile-dev-harness · job 75%android_mcp · job 76%AutoMobile · job 84%Mobilerun MCP · job 91%Tasker MCP · job 74%Multi-UIAutomator2 · job 82%Layout Debug MCP · job 72%android_ui_mcp · job 73%Android Autopilot MCP · job 87%mcp-hands · job 74%Oh My Android · job 84%Phone for AI · job 86%Auto Phone · job 85%TextBee MCP · job 72%ADB MCP Server · job 76%glass · job 76%rPlay SDK · job 75%ARTEMIS Harness · job 80%deepadb · job 82%android_remote_control_mcp · job 87%waydroid_mcp · job 83%Android-MCP-go · job 82%DroidBridge · job 87%MCP Appium · job 77%jevdevice · job 74%Android Use · job 89%Android ADB MCP Server · job 87%screenhand · job 82%mobilenext_mcp · job 78%android-mcp · job 83%scrcpy_mcp · job 87%Karagöz · job 84%airi_android · job 79%Zeptap · 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