sleepon-mcp
OfficialClick on "Install Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@sleepon-mcpanalyze my sleep from last night"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
Sleepon MCP Server
An MCP (Model Context Protocol) server that connects AI assistants like Claude to your Sleepon sleep tracker data. Ask your AI to analyze your sleep quality, compare nights, generate reports, and get personalized improvement tips — all powered by your real sleep data.
Features
🛏️ Daily Sleep Summary — sleep score, efficiency, duration, and stage breakdown
📊 Detailed Segments — per-segment heart rate, blood oxygen (SpO2), HRV, movement, and ODI
📅 Sleep Calendar — see which days have data over a date range
📈 Trend Analysis — track how your sleep metrics change over time
🏷️ Sleep Labels — view user-added tags (e.g. "exercised", "drank coffee") and notes
🤖 Built-in Prompts — one-click deep analysis, comparison, reports, and improvement tips
Related MCP server: Oura Ring MCP Server
Quick Start
1. Install
# Using uvx (recommended, auto-downloads without install)
uvx sleepon-mcp
# Or install via pip
pip install sleepon-mcp2. Configure Claude Desktop
To use this MCP server with Claude Desktop, you need to add it to your configuration file.
Step 1: Open the configuration file based on your operating system:
macOS:
~/Library/Application Support/Claude/claude_desktop_config.jsonWindows:
%APPDATA%\Claude\claude_desktop_config.json
(Tip: You can quickly open this from Claude Desktop: Menu -> Settings -> Developer -> Edit Config)
Step 2: Add the sleepon server to the mcpServers object. Replace the email and password with your actual Sleepon account credentials.
{
"mcpServers": {
"sleepon": {
"command": "uvx",
"args": ["sleepon-mcp"],
"env": {
"SLEEPON_USERNAME": "your-sleepon-email@example.com",
"SLEEPON_PASSWORD": "your-password"
}
}
}
}Note: uvx is recommended as it automatically manages the Python environment for you. If you prefer to use your system Python, you can use "command": "python", "args": ["-m", "sleepon_mcp.server"] instead.
⚠️ Troubleshooting:
spawn uvx ENOENTError If Claude Desktop shows anENOENTerror, it means it cannot find theuvxcommand in its system path. To fix this, you must provide the absolute path touvx.
Open your terminal and run
which uvx(Mac/Linux) orwhere uvx(Windows).Copy the resulting path (e.g.,
/Users/username/.pyenv/shims/uvxorC:\\Users\\username\\.cargo\\bin\\uvx.exe).Replace
"uvx"in the"command"field of the config with this absolute path.
3. Restart Claude Desktop
Completely quit Claude Desktop (
Cmd+Qon Mac, or right-click the system tray icon and exit on Windows).Re-open Claude Desktop.
Look for the hammer icon (🔨) in the chat input area. Click on it to see the available Sleepon tools and prompts.
Available Tools
Tool | Description |
| Verify that your credentials are correct and the API is reachable |
| Get your Sleepon user profile information |
| Get complete sleep summary for a specific date |
| Get detailed segment data (heart rate, SpO2, HRV, sleep stages) |
| View which days have data in a date range |
| Get sleep metric trends over a date range |
| Get user-added sleep labels and notes for a date |
| Find the most recent data sync timestamp |
Built-in Prompts
These prompts guide the AI through multi-step analysis workflows:
Prompt | Description |
| Comprehensive analysis of a single night (summary + segments + labels) |
| Side-by-side comparison of two nights with tables |
| Full report for a date range (trends, best/worst days, health alerts) |
| Personalized recommendations based on your recent data |
Example Conversations
"Analyze my sleep from last night"
"Compare my sleep on Monday vs Friday"
"Generate a sleep report for the past month"
"How can I improve my sleep quality?"
Development
# Clone the repo
git clone https://github.com/sleepon-official/sleepon_mcp.git
cd sleepon_mcp
# Install in development mode
pip install -e .
# Test with MCP Inspector
npx -y @modelcontextprotocol/inspector sleepon-mcpEnvironment Variables
Variable | Required | Description |
| Yes | Your Sleepon account email |
| Yes | Your Sleepon account password |
Requirements
Python >= 3.10
A Sleepon account with a paired sleep tracker
License
This server cannot be installed
Maintenance
Resources
Unclaimed servers have limited discoverability.
Looking for Admin?
If you are the server author, to access and configure the admin panel.
Latest Blog Posts
- Your AI Chatbot Just Exposed Your CEO's Salary to an InternBy Om-Shree-0709 on .Agent IdentityMCP SecurityOAuth Delegation
- Why MCP Servers Need Execution Sandboxing (And Why Your Current Stack Isn't Enough)By Om-Shree-0709 on .Agentic AiPrompt InjectionWebAssembly
MCP directory API
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/sleepon-official/sleepon_mcp'
If you have feedback or need assistance with the MCP directory API, please join our Discord server