$ loading_
Securely let AI access, query, and update normalized user-controlled health data.
Copy the install command and let the AI configure it · recommended for beginners
No copy-paste install info for "Heavenly Health Protocol" yet — see the docs or source repo.
Use Heavenly Health Protocol to query my step count and sleep duration for the last 30 days, then summarize the main trends.
A summary of the last 30 days of steps and sleep data, with trend insights.
Use Heavenly Health Protocol to update today's weight record to 68.4 kg and confirm the write result.
The health data is written successfully, with a confirmation of the update result.
Explain how to connect a user-controlled health data source with Heavenly Health Protocol, such as Apple Health or Supabase.
An overview of supported data sources and connection approach, including optional OAuth details.
Developers can connect this tool to an AI health assistant so the model can query or update user-authorized health data within a bounded tool set. This enables real health-data workflows while maintaining clear access boundaries and security.
When a team needs to work with user health data from sources like Apple Health or Supabase, this protocol can access normalized data. That makes it more suitable for unified querying, analysis, or downstream AI workflows.
For projects with stricter privacy and security requirements, teams can use its sandboxed deployment approach to run the MCP tool. This helps reduce exposure risks when connecting health data to AI clients.
It is an MCP tool that lets AI clients securely access, query, and update normalized, user-controlled health data. The description mentions sources such as Apple Health and Supabase.
It supports optional OAuth and limits actions through a bounded set of MCP tools. The original description also mentions sandboxed deployment for stronger security.
Based on the given information, it is designed for normalized health data and emphasizes user control, secure access, and a bounded action set for AI clients. For deeper implementation details, see the source repository.
Query Google Health fitness data in natural language for quick personal insights.
Query and export Apple Health data with trends, comparisons, and structured results.
Sync workouts and nutrition data through one MCP interface for analysis.
Access Google Health metrics and optionally sync them into Obsidian notes.
Integrate compliant healthcare AI via MCP for enterprise-ready development workflows.
Access daily health metrics, baselines, and a stable daily health summary.