Connect Sports Science Research to Claude Code
Query Sports Science Research directly from Claude Code. Arlet links the two through one MCP connection and takes care of API keys.
Covers the sports-science literature from the published record through to preprints.
Tools:
- search_sports_science: Europe PMC with an exercise/sports filter. The major journals in the field (Sports Medicine, Medicine & Science in Sports & Exercise, Journal of Applied Physiology) are indexed here, and open-access records include the abstract.
- search_sports_medicine_studies: PubMed narrowed with MeSH terms (Sports, Athletic Performance, Exercise, Physical Endurance) for MeSH-level precision. Metadata and links only.
- search_sportrxiv_preprints: SportRxiv on OSF, for findings not yet journal-published. This is the single home for SportRxiv across the healthcare servers - SportRxiv covers strength and endurance alike, so the strength-training server links here instead of duplicating the search.
Using two literature tools is intentional: Europe PMC gives broader coverage plus open-access abstracts, while PubMed's controlled vocabulary keeps a broad query from drifting off topic. Start with Europe PMC, then use PubMed when precision matters.
Abstracts are returned only for open-access articles under a CC license; other records carry metadata and a link, because abstract text remains the publisher's copyright.
This server reports what studies found. It does not prescribe training or treat injuries, and it is not medical advice.
How to connect Sports Science Research to Claude Code
- 1
In the Arlet dashboard, open Data tools, find Sports Science Research and switch it on. No API key setup is needed.
- 2
In your terminal, run claude mcp add --transport http arlet https://mcp.arlet.dev/mcp/ to add Arlet as an MCP server.
- 3
Start Claude Code, run /mcp, select arlet and click Authenticate.
- 4
Your browser opens. Sign in with Google and click Allow on the consent screen. The connection is complete.
The connection is per user and works across every project on the same machine.
