mcp · handle garmin_owl
garmin_claude_mcp · job 74%Garmin Connect China MCP · job 79%whoopmcp · job 76%Cronometer Core · job 74%garmin_athletics_mcp · job 79%Garmin MCP · job 71%Futureweb Intervals MCP Server · job 73%Garmin Connect API · job 72%Apple Workouts MCP · job 73%garmin-watch-mcp · job 86%Wellness Project MCP · job 78%RunFuel MCP · job 83%Sunsynk Solar MCP Server · job 71%garmin-mcp · job 78%Garmin Health MCP · job 81%Garmin Connect MCP · job 91%Garmin Personal MCP Demo · job 78%Paceva for Garmin · job 82%Running Companion · job 79%Gear MCP · job 74%Garmin Connect to ChatGPT MCP · job 71%Google Health MCP · job 74%Zone Two · job 72%Garmin Local Archive · job 82%Garmin Personal MCP · job 84%ownmetrics-mcp · job 78%Garmin MCP Server · job 76%FitnessPeak · job 75%garmin_connect_mcp · job 74%PaceLine Local · job 74%gpx-mcp · job 72%Threshold · job 72%bodyledger · job 73%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