Strava
This MCP server provides AI assistants with access to Strava fitness data through local caching and rate limit management, built by Lyle Dean using Go with Gin web framework, zstd compression for storage, and OAuth token management. The implementation offers three core tools for retrieving and filtering Strava activities with date range support, accessing detailed sensor stream data including GPS coordinates, heart rate, and power metrics, and refreshing cached data from the Strava API with configurable time windows. Built with compressed local storage using zstd, automatic token refresh handling, and dual deployment modes supporting both MCP protocol and standalone REST API, it serves fitness enthusiasts wanting conversational access to their workout data, coaches needing AI-assisted training analysis, and developers building fitness applications who require cached Strava integration with intelligent rate limit management.
Composite of vulnerability cleanliness, spec conformance, provenance, stability, and usage signals — scanned and weighted by Cognium. Human and agent signals are tracked separately. Last scanned 2026-09-02.
Scan details: Circle-IR · 2026-09-02 · Appeal
View full trust & usage report →Metadata
- Version
- 1.0.0
- Skill type
- atomic
- Execution layer
- mcp-remote
- Category
- devops-ci
- Source
- PulseMCP
- Repository
- github.com/lyledean1/strava-mcp
- Author type
- human
- Last scanned
- 2026-09-02
- Updated
- 2026-09-02
Use via MCP
Resolve Strava from your agent
Streamable HTTP transport at https://api.skillsregistry.net/mcp. No auth for read tools. Discovery: .well-known/mcp.json.
One command in your shell — Claude Code wires it up and verifies the connection. Run /mcp in any session to confirm.
claude mcp add --transport http --scope user skillsregistry https://api.skillsregistry.net/mcp--scope user for --scope project to commit it to .mcp.json.