Sport Health MCP
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| SPORT_HEALTH_EXPORT_DIR | Yes | Path to the Huawei health data export directory (HUAWEI_HEALTH_* folder). |
Instructions
Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.
This server publishes no instructions, or was last inspected before Glama recorded them.
Capabilities
Features and capabilities supported by this server
Protocol revision2025-11-25
| Capability | Details |
|---|---|
| tools | {
"listChanged": false
} |
| prompts | {
"listChanged": false
} |
| resources | {
"subscribe": false,
"listChanged": false
} |
| experimental | {} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| inspect_huawei_exportA | Check the configured Huawei export and report available source-file counts. |
| list_activitiesA | List imported activities. Optionally filter by running, walking, cycling, fitness, or workout. |
| get_activity_summaryC | Get normalized summary metrics for one activity. |
| get_activity_trackA | Get a paginated GPS track with timestamps and altitude for one activity. |
| get_activity_samplesA | Get paginated heart_rate, cadence, speed, altitude, or pace samples. |
| get_health_contextA | Get daily health summaries around an activity, including sleep, HRV, stress, heart rate, and SpO2. |
| get_activity_environmentB | Fetch cached historical weather and air-quality context from Open-Meteo. |
| get_report_evidence_packA | Build deterministic facts, context, flags, and guidance for a post-activity Agent report. |
| get_report_contractA | Return the stable structure and writing rules for end-user activity reports. |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
TDQS
Scored across 9 tools
Each tool maps cleanly to a distinct resource or data type: Huawei source inspection, activity listing, activity summary, GPS track, samples, health context, weather environment, report evidence, and report contract. Even the health context and activity environment tools are clearly separated by source and intent.
Most tools follow a clear get_<object> pattern, such as get_activity_summary, get_activity_track, and get_report_contract. The deviations are minor: list_activities uses list instead of get, and inspect_huawei_export uses inspect, but all are still recognizable, verb-first names.
Nine tools is a well-scoped surface for an activity and report analysis server. Each tool represents a meaningful step in the workflow—from inspecting source files, listing and retrieving activity data, adding health/environment context, and producing report evidence and contract rules.
The tool set forms a complete read-only pipeline for activity reporting: find source files, list activities, fetch summary, track, samples, health context, environmental context, and then produce evidence and contract for the final agent report. There are no obvious dead ends or missing operations within this server's reporting-focused scope.