1st Place: Design Secure Agent-to-Agent Systems | Descope Global MCP Hackathon

Sticking to a fitness routine can be difficult, especially for beginners, older adults, or people managing health conditions. Choosing the right exercises, meals, and recovery methods is often confusing, and most tools don’t personalize guidance in a meaningful way. AI Fitness Agent set out to solve this by creating a system of specialized agents that work together to provide tailored fitness, nutrition, and recovery support.

Users log in once through a Descope-secured flow, and from there scoped JWT tokens govern every interaction between agents. A FastAPI orchestrator routes user queries to the right agent—Trainer, Nutrition, or Recovery—and aggregates their responses. The system can even integrate Fitbit data to provide recovery insights, making the guidance both personalized and dynamic.

LINKS
🔹 Repo: https://github.com/GouthamCharan06/Fitness-Agent
🔹 MCP Hackathon: https://globalmcphackathon.com/
🔹Descope for AI: https://www.descope.com/use-cases/ai
🔹Descope docs: https://docs.descope.com
🔹Descope community: https://www.descope.com/community

SOCIALS
🔹 Descope GitHub: https://github.com/descope
🔹Descope LinkedIn: https://www.linkedin.com/company/descope/mycompany
🔹Descope X: https://twitter.com/descopeinc

#mcphackathon #hackaton #agenticai #modelcontextprotocol

Видео 1st Place: Design Secure Agent-to-Agent Systems | Descope Global MCP Hackathon канала Descope