eufylife-mcp
An MCP server for EufyLife smart scale body composition data, exposing weight, BMI, body fat, muscle mass, and 20+ other measurements as tools for AI assistants.
README
eufylife-mcp
An MCP (Model Context Protocol) server for EufyLife smart scale body composition data. Exposes your weight, BMI, body fat, muscle mass, and 20+ other measurements as tools that AI assistants can use.
Built by reverse-engineering the EufyLife cloud API, based on the work done by @m4ary in eufylife-api-hacs.
Features
- Authenticate with your EufyLife cloud account
- Retrieve latest and historical body composition measurements
- Multi-user support — list family member profiles sharing the same scale
- List connected devices and their configuration
- 20+ body composition measurements (weight, BMI, body fat, muscle mass, bone mass, BMR, body age, water percentage, protein ratio, visceral fat, and more)
- Auto-login via environment variables
- Token auto-refresh (tokens valid ~30 days)
Prerequisites
- Bun runtime (v1.0+)
- A EufyLife account with a connected smart scale
Installation
From npm (recommended)
bunx eufylife-mcp
From source
git clone https://github.com/MatthewHallCom/eufylife-mcp.git
cd eufylife-mcp
bun install
bun run src/index.ts
Configuration
Environment Variables
| Variable | Description |
|---|---|
EUFYLIFE_EMAIL |
Your EufyLife account email |
EUFYLIFE_PASSWORD |
Your EufyLife account password |
When both are set, the server auto-authenticates on startup. Alternatively, use the login tool at runtime.
Claude Code
Add to your project's .mcp.json file:
{
"mcpServers": {
"eufylife": {
"command": "bunx",
"args": ["eufylife-mcp"],
"env": {
"EUFYLIFE_EMAIL": "your@email.com",
"EUFYLIFE_PASSWORD": "your-password"
}
}
}
}
Or add to .claude/settings.local.json:
{
"mcpServers": {
"eufylife": {
"command": "bun",
"args": ["run", "src/index.ts"],
"cwd": "/path/to/eufylife-mcp",
"env": {
"EUFYLIFE_EMAIL": "your@email.com",
"EUFYLIFE_PASSWORD": "your-password"
}
}
}
}
Other MCP Clients
This server uses stdio transport and works with any MCP-compatible client. Point your client at:
bunx eufylife-mcp
Set EUFYLIFE_EMAIL and EUFYLIFE_PASSWORD as environment variables.
Available Tools
login
Authenticate with EufyLife cloud.
| Parameter | Type | Required | Description |
|---|---|---|---|
email |
string | yes | EufyLife account email |
password |
string | yes | EufyLife account password |
Returns user ID, customer profiles, and connected devices.
get_measurements
Get the most recent body composition measurement for each user/family member.
| Parameter | Type | Required | Description |
|---|---|---|---|
customer_id |
string | no | Filter by specific customer/family member |
get_measurement_history
Get historical measurements since a given date.
| Parameter | Type | Required | Description |
|---|---|---|---|
since |
string | no | ISO 8601 date (e.g. 2024-01-01) |
customer_id |
string | no | Filter by specific customer/family member |
Returns all measurements after the given date. Omit since to get full history.
list_users
List all customer/family member profiles associated with the account. Returns name, sex, height, birthday, target weight, and member type for each user. No parameters.
get_device_info
List all connected EufyLife devices with model info, product code, BLE MAC, weight unit setting, and room assignment. No parameters.
Available Resources
| URI | Description |
|---|---|
eufylife://users |
JSON list of customer/family member profiles |
eufylife://measurements/{customer_id} |
Latest measurements for a specific customer |
Supported Measurements
All measurements from the EufyLife smart scale scale_data response:
| Measurement | Unit | Field |
|---|---|---|
| Weight | kg | weight_kg |
| BMI | kg/m² | bmi |
| Body Fat | % | body_fat_pct |
| Subcutaneous Fat Rate | % | subcutaneous_fat_rate_pct |
| Visceral Fat Index | index | visceral_fat_index |
| Muscle | % | muscle_pct |
| Muscle Mass | kg | muscle_mass_kg |
| Skeletal Muscle Mass | kg | skeletal_muscle_mass_kg |
| BMR (Basal Metabolic Rate) | kcal/day | bmr_kcal |
| Bone | kg | bone_kg |
| Bone Mass | kg | bone_mass_kg |
| Water | % | water_pct |
| Body Age | years | body_age_years |
| Protein Ratio | % | protein_ratio_pct |
| Visceral Fat | level | visceral_fat_level |
| Fat Free Weight | kg | fat_free_weight_kg |
| Body Fat Mass | kg | body_fat_mass_kg |
| Heart Rate | bpm | heart_rate_bpm |
| Body Type | type | body_type |
| Height | cm | height_cm |
Not all scales report every measurement. Fields that are unavailable or zero from the API are returned as null.
Supported Devices
This server works with EufyLife smart scales that use the EufyLife cloud API, including:
| Model | Product Code |
|---|---|
| Smart Scale P1 | T9147 |
| Smart Scale P2 Pro | T9149 |
| Smart Scale P3 | T9150 |
| Smart Scale C1 | T9146 |
| Smart Scale A1 | T9960 |
| Smart Scale | T9140 |
Other EufyLife/Anker smart scales that sync to the EufyLife app should also work.
Local Development
# Install dependencies
bun install
# Run the server
bun run src/index.ts
# Type check
bun x tsc --noEmit
# Explore the raw API (requires .env with credentials)
bun run scripts/explore-api.ts
How It Works
This server communicates with the undocumented EufyLife cloud API (api.eufylife.com) used by the official EufyLife iOS/Android app. The API interaction patterns were derived from the eufylife-api-hacs Home Assistant integration.
Key API endpoints:
POST /v1/user/v2/email/login— authenticate and get user/device/customer dataGET /v1/device/data— fetch scale measurements (supports?after={timestamp}for incremental)GET /v1/customer/target/{id}— fetch per-customer target weight and goals
Limitations
- Unofficial API — Uses the undocumented EufyLife cloud API. It may break if EufyLife changes their API.
- Cloud-only — Requires internet access to fetch data from EufyLife servers. No local/BLE support.
- Read-only — This server only reads data. It cannot modify settings, delete measurements, or control devices.
- Token expiry — Tokens are valid for ~30 days. The server auto-refreshes when credentials are stored.
Credits
- eufylife-api-hacs by @m4ary — the Home Assistant integration that this project's API implementation is based on.
- Model Context Protocol — the protocol that enables AI assistants to use this server.
License
MIT
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.