SportsTrackLive
VerifiedFeaturedRemoteAbout SportsTrackLive
SportsTrackLive is a remote MCP server available at https://mcp.sportstracklive.com. SportsTrackLive is a Live Tracking solution and let you record, share and relive your Tracks! SportsTrackLive provide a real-time tra
Configuration
Remote servers need no local install. Pick your client, then copy the config or install in one click.
https://mcp.sportstracklive.com/mcpclaude mcp add --transport http sportstracklive https://mcp.sportstracklive.com/mcp{"mcpServers":{"sportstracklive":{"type":"http","url":"https://mcp.sportstracklive.com/mcp"}}}Open in Cursor{"servers":{"sportstracklive":{"type":"http","url":"https://mcp.sportstracklive.com/mcp"}}}Open in VS Code{"mcpServers":{"sportstracklive":{"type":"http","url":"https://mcp.sportstracklive.com/mcp"}}}{"mcpServers":{"sportstracklive":{"serverUrl":"https://mcp.sportstracklive.com/mcp"}}}Run commands in a terminal; paste JSON into the client’s MCP config and restart. Servers that need sign-in will prompt on first connect.
Tools
8| Parameter | Type | Required | Description |
|---|---|---|---|
| filename | string | Yes | File name including its extension — the extension selects the parser. Supported: .gpx, .tcx, .igc, .sbp, .fit |
| file_base64 | string|null | No | The file content, base64-encoded. Maximum 8 MiB decoded. Provide either this or `file_url`. Prefer `file_url` for files over ~100 KB: it keeps the payload out of the conversation. |
| file_url | string|null | No | Public https:// URL of the file (e.g. a cloud share or export link); the server downloads it (15 MiB cap). Provide exactly one of `file_url`, `upload_id` or `file_base64`. |
| upload_id | string|null | No | Id returned by POST https://mcp.sportstracklive.com/upload — the way to analyze a LOCAL file when a shell is available: run `curl -s -X POST https://mcp.sportstracklive.com/upload --data-binary @/path/to/file` (one command, the file content never enters the conversation), then pass the returned upload_id here with the original filename. |
| sport | any | No | Sport of the activity. Use "auto" (default) to let the server infer it from the file format and trace kinematics; the resolved sport is returned in `context_used.sport` and can be overridden on a second call. |
| measure_unit | any | No | Preferred units for the computed metrics ("metric" default, or "imperial"). |
| detail | any | No | "standard" (default) returns every computed insight but strips the bulky point-level payloads (per-phase segment lists, wind timeline, pause/trim ranges) — a few KB instead of tens. "full" returns the raw engine output unabridged. |
Details
The maintainer has not added details yet. Check the README in the repository.
Comments
New to MCP?
From what the protocol is to installing your first server, these answers cover most first questions.
An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.