mcp · handle running_companion
Threshold · job 79%ownmetrics-mcp · job 75%hybridlog · job 73%garmin_connect_mcp · job 76%Pushing Limits MCP · job 72%garmin-watch-mcp · job 85%Garmin Connect to ChatGPT MCP · job 79%Garmin Connect API · job 74%Garmin Connect MCP · job 78%Futureweb Intervals MCP Server · job 73%garmin-owl · job 79%Paceva for Garmin · job 90%garmin-mcp · job 84%Garmin MCP · job 70%Garmin Health MCP · job 75%RunFuel MCP · job 79%Garmin Personal MCP · job 77%Zone Two · job 81%garmin_athletics_mcp · job 83%Garmin MCP Server · job 74%garmin-cn-ai-trainlab · job 72%garmin_claude_mcp · job 74%Garmin AI Connector · job 72%Garmin Connect China MCP · job 77%Kailo MCP Server · job 75%Intervals Training Bridge · job 73%Garmin Personal API MCP · job 76%Garmin Local Archive · job 75%Garmin Assistant · 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