durability-mcp
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| DURABILITY_FIT_DIR | Yes | Path to the folder containing your FIT files |
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
} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| list_durability_runsB | List outdoor runs with status signal, no_signal or not_evaluable. Dates are YYYY-MM-DD. No GPS is returned. |
| get_durability_indicesA | Return drift, magnitude, onset and gate status for one run, or why it cannot be evaluated. No GPS is returned. |
| get_durability_trendB | Summarise runs over time and compare the latest runs with this runner's own earlier runs. No prediction is made. |
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 3 tools
Each tool has a distinct scope: listing runs, evaluating one run's indices, and summarizing/trending over time. The descriptions explicitly delimit one-run vs aggregate analysis, so boundaries are clear.
All three names follow the same snake_case verb_durability_noun pattern: list_durability_runs, get_durability_indices, get_durability_trend. No mixed conventions or vague verbs.
Three tools are well-scoped for a focused read-only durability analytics server: list, detail, and trend. Each earns its place without redundancy.
The surface covers the natural read-only workflow: discover runs, inspect per-run durability indices with non-evaluable explanations, and compare trends over time. No create/update/delete is needed for this analysis-only domain.