About Vytallink
Vytallink is an MCP server published by xmartlabs in the Developer Tools category: vytalLink is a digital health platform connecting personal health data—including Apple Health, Google Fit, and wearables—with AI assistants like ChatGPT and Claude. Includes a Flutter app, Node.js MCP server, and Firebase landing page. Focused on privacy and user control.
The repository has 6 stars and 0 forks, with the last commit 6 months ago. Six months or more without a commit doesn't mean the server is broken, but check the open issues before depending on it in production.
Install
git clone https://github.com/xmartlabs/vytalLinkThis server has no ConduID identity, so agent calls to it are not receipted. Pin the version you install and review the source before granting it credentials.
Ask AI
Ask AI about Vytallink
Powered by Claude · Grounded in docs
Security checks
- ✓README presentThe repository ships documentation.
- ✓License declaredUsable under a stated license.
- !Scoped permissionsDoesn't declare a permission scope. Assume it can do anything its process can.
3 checks have not been run yet.
Releases
README
VytalLink Monorepo
VytalLink brings your personal health metrics to life by collecting Apple HealthKit or Google Health Connect data and exposing it through an MCP-compatible interface, so any AI assistant can query it securely from your own device. Learn more at vytallink.xmartlabs.com.
We initially launched this repository as a Flutter mobile application that bundled its own MCP server; the full story is captured in our blog post “Building Health Apps with MCP + LLMs.” To make the experience more accessible and less dependent on technical setup, we shifted toward a GPT integration backed by a cloud-hosted MCP server, keeping this app as the bridge between the two worlds. If you want to explore the original local MCP server version, you can still find it at github.com/xmartlabs/vytalLink/tree/1.0.0.
This monorepo hosts every piece of the product experience:
- mobile/ — Flutter application that runs on device and exposes the embedded MCP server.
- landing/ — Static marketing site deployed to Firebase Hosting.
- mcp-server/ — Standalone MCP server (Node.js) intended to run outside the mobile app.
- examples/ — TypeScript and Python agent examples that consume the MCP server.
- docs/ — Shared documentation (coding standards, contribution guides, etc.).
Each folder contains its own README with the detailed setup. This document only summarizes the repository layout.
Global prerequisites
- Flutter + FVM (see
.fvmrc). - Node.js with your preferred package manager (npm, pnpm) for the web/Node portions.
- Python 3.11+ if you plan to run the Python agent example.
- Firebase CLI if you plan to deploy the landing or use hosting commands.
Examples quick start
# Helpers for both examples
(cd examples && ./scripts/repo.sh help)
# TypeScript example
cd examples/athletic-analyst-ts && npm run agent -- --mode readiness
# Python example
cd examples/athletic-analyst-py && python -m src.main --mode readiness
Documentation
- Repository guidelines:
AGENTS.md. - Coding standards:
docs/CODE_STANDARDS.md. - Consolidated guidelines:
docs/CONSOLIDATED_GUIDELINES.md. - Add any new repository-wide guides under
docs/.
Building an integration? Start with
llms.txt— an AI-friendly overview of the product, API reference, and integration gotchas.
Contributing
- Create a descriptive branch.
- Run the checks for every package/app you touched.
- Open a pull request referencing the relevant issues or tickets.
License
MIT License. See individual project READMEs for any additional notes.
Made with ❤️ by Xmartlabs.
README copy captured when this server was indexed; it may lag the repository. The original is authoritative.