​
What is MCP?

The Model Context Protocol (MCP) is an open standard that enables AI applications to securely connect to external data sources and tools. Think of it as a bridge that allows AI models like ChatGPT, Claude, or your custom AI application to access real-world data and perform actions on your behalf.

​
Spike’s MCP Server

Spike provides a ready-to-use MCP server that makes health and fitness data accessible to AI applications. This means you can ask AI assistants natural language questions about your health data, and they can automatically fetch, analyze, and interpret information from your connected wearables and health devices. The MCP server handles authentication, data retrieval, and formatting, so AI applications can focus on analysis and user interaction rather than API integration complexity. For more information about how to use the MCP server, see the Implementation Guide. For a list of available MCP tools, see the Tools page.

​
Common Use Cases

​
Personal Health Analysis

Ask AI assistants to analyze your health trends and provide insights:
  • “How has my sleep quality changed over the past month?”
  • “Compare my activity levels between weekdays and weekends”
  • “What patterns do you see in my heart rate data?”

​
Health Coaching & Recommendations

Get personalized recommendations based on your actual data:
  • “Based on my recent sleep patterns, what should I focus on to improve my rest?”
  • “Suggest workout adjustments based on my recovery metrics”
  • “How can I improve my daily step count given my current trends?”

​
Data Correlation & Discovery

Uncover relationships between different health metrics:
  • “Is there a correlation between my sleep duration and next-day activity levels?”
  • “How does my heart rate variability relate to my stress levels?”
  • “What impact does my workout intensity have on my recovery time?”

​
Health Reporting & Summaries

Generate comprehensive health reports automatically:
  • “Create a weekly health summary for my doctor’s appointment”
  • “Summarize my fitness progress over the last quarter”
  • “Generate a sleep quality report for the past two weeks”

​
User Dataset Integration

Combine your own datasets with health metrics for comprehensive analysis:
  • “Analyze my symptom diary alongside my heart rate variability and stress levels”
  • “How do my mood entries correlate with my sleep quality and activity levels?”
  • “Compare my productivity journal with my energy levels and recovery metrics”
  • “Identify patterns between my medication timing and heart rate data”

​
Personalized Health Research

Conduct your own health studies using combined data sources:
  • “Track how my meditation practice affects my HRV and resting heart rate”
  • “Analyze the relationship between my diet log and my sleep duration”
  • “How does my work stress level (from my journal) impact my recovery score?”
  • “Find correlations between my supplement intake and energy levels”

​
Application Integration

Build AI-powered features into your health applications:
  • Automated health insights in mobile apps
  • Personalized coaching recommendations
  • Natural language health data queries
  • Intelligent health trend analysis
  • User-provided dataset correlation analysis