One MCP endpoint for many AI tools
Connect wearables, CGMs, power meters, and gym apps through a private MCP endpoint, then use that endpoint in Claude, ChatGPT, Claude Code, or any MCP-compatible client.
freddy
freddy connects wearable, CGM, training, and gym data to AI assistants like Claude and ChatGPT through a private MCP server. It lets you ask natural-language questions about sleep, recovery, HRV, glucose, and workouts using your own metrics.
What freddy is
freddy is a personal health MCP server that connects wearables, CGMs, power meters, and gym apps to AI assistants such as Claude, ChatGPT, Claude Code, and other MCP-compatible clients. Instead of switching between device dashboards, you can ask questions about your own data in plain language and get answers grounded in the numbers freddy serves.
The product is built around read-only access to connected sources and a single private endpoint. The site says setup takes about 90 seconds: connect a source with OAuth, paste the MCP URL into your AI tool, and start asking about sleep, recovery, HRV, training load, glucose response, and workouts. It also emphasizes export and deletion controls for people who want to remove their data later.
Core capabilities
Natural-language analysis of health data
Ask questions in natural language and get answers grounded in your actual metrics, such as HRV, sleep, glucose, recovery, training load, and workout data.
Quick connection flow
Set up by signing up, connecting a source with OAuth, and pasting your MCP URL. The site says the process takes about 90 seconds.
Privacy-focused access model
Use a read-only integration that is revocable, with encrypted tokens and an audit log. The site says freddy never trains on or shares your data.
Prompt recipes for common analyses
Start from starter prompts in the public recipe book, including questions about sleep, trends, glucose response, and training plateaus.
Data export and deletion
Export your history as CSV or delete your account and connected data if you want to leave.
Practical ways to use freddy
Investigate recovery patterns
Look at HRV, sleep fragmentation, training load, and resting heart rate together to understand whether a poor recovery week is a one-off or part of a trend.
Review glucose response
Ask how glucose behaves after meals or across the day, then compare it with sleep or training context instead of reading numbers in a separate app.
Track strength progress
Check which lifts have plateaued and for how long, using your workout history rather than manually comparing logs across gym apps.
Analyze training trends
Compare this month with last month, ask what changed, or inspect whether your Zone 2 work lines up with HRV drift and overall load.
Explore with prompt recipes
Use starter prompts from the recipe book to turn a vague question into a concrete analysis while you are already in Claude or ChatGPT.
Pros and Cons
Pros
- Connects many health and fitness sources into one AI-accessible endpoint.
- Works with several major AI assistants, including Claude and ChatGPT.
- Supports natural-language questions across sleep, HRV, glucose, training, and workouts.
- Uses read-only, revocable connections with encrypted tokens and an audit log.
- Offers CSV export and one-click deletion for account and data cleanup.
Cons
- Source coverage is still expanding, and some connectors are listed as planned or beta rather than live.
- The product is designed for AI tools that support MCP, so it depends on using a compatible assistant or client.
FAQ
Is my health data safe and can I disconnect a source later?
Yes. freddy is read-only for connected sources, and the site says tokens are encrypted at rest with AES-256. It also says you can disconnect sources later and revoke access in one click.
How does setup work?
The site says setup takes about 90 seconds: sign up, authorize a source through OAuth, and paste your MCP URL into an AI tool that supports MCP.
Which AI tools can use freddy?
freddy is built for ChatGPT, Claude, Claude Code, and other MCP-compatible clients. The site also mentions support for agents such as OpenClaw and Hermes.
What kinds of data can I ask about?
The site says freddy serves over 100 metrics and supports sleep, HRV, glucose, power, sleep stages, lifts, and more from connected wearables and training apps.
Can I export or delete my data?
The site says you can export your history as CSV and delete your account, connectors, history, and stored data in a couple of clicks.
Quick Facts
- Product type
- Personal health MCP server
- Primary use
- Ask AI questions about wearable and training data
- Supported AI tools
- Claude, ChatGPT, Claude Code, and other MCP clients
- Integrations
- Oura, WHOOP, Polar, Garmin, Dexcom, Hevy, Suunto, Withings, Intervals.icu, Concept2, and more
- Setup
- OAuth a source, then paste the MCP URL
- Website
- freddy.coach
freddy 대안
Lasso
Lasso is an ecommerce product data platform for enriching catalog records, processing supplier files, generating product content, and monitoring competitors. It combines a web app with a REST API, SDK, and MCP server for teams and developers.
MIRA vision
MIRA vision develops synthetic-data-driven AI for pathology image analysis in medical diagnostics. Its website positions the product for teams that need privacy-compliant training data, automatic annotations, and controlled data generation.
Tavus
Tavus is an AI video platform for building real-time, face-to-face agents, digital twins, and AI companions. It combines APIs, custom replicas, and multilingual conversational workflows for developers and teams.
HiringPartner.ai
HiringPartner.ai is an autonomous AI recruiting platform for sourcing, screening, and interviewing candidates 24/7. It supports ATS-connected workflows, bulk resume uploads, and reviewable interview outputs for hiring teams.
Teloframe
Teloframe is an AI-powered football coaching platform for building tactics, editing drills, planning sessions, and managing player development in one workspace. It includes a Free tier plus Pro and Club plans for coaches and analysts who need more collaboration and team features.
TrakMac
TrakMac is a voice-first macro tracking app for fitness-focused users on iOS. It estimates calories and macros from spoken meal descriptions, then helps users log food and stay aligned with their training goals.