BabyBuddy MCP Server
Click 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., "@BabyBuddy MCP ServerLog a wet diaper change for Emma"
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.
BabyBuddy MCP Server
MCP server for self-hosted BabyBuddy.
Transport: Streamable HTTP (runs on http://localhost:8080)
Auth: Direct API Token via environment variables. No login required.
Quick Start
1. Install
cd babybuddy-mcp
pip install -r requirements.txt2. Configure
Set the following environment variables in your .env file or shell:
Variable | Description |
| Your full BabyBuddy URL (e.g., |
| Your API token (Settings → API → your token) |
Optional:
Variable | Default | Description |
|
| Bind address |
|
| Listen port |
|
| Public base URL |
3. Run
python3 server.pyRelated MCP server: MCP Nightscout
Tools (33 total)
Tool | Description |
| List all children (returns IDs needed by other tools) |
| Log a feeding — type, method, start/end, optional amount |
| Recent feedings for a child |
| Delete a feeding session by ID |
| Log a sleep session (nap or night) |
| Recent sleep sessions |
| Delete a sleep session by ID |
| Log a diaper change — wet, solid, color, amount |
| Recent diaper changes |
| Delete a diaper change by ID |
| Log temperature in °C |
| Recent temperature readings |
| Delete a temperature reading by ID |
| Log weight in kg |
| Weight history |
| Delete a weight measurement by ID |
| Log height in cm |
| Height history |
| Delete a height measurement by ID |
| Log head circumference in cm |
| Head circumference history |
| Delete a head circumference measurement by ID |
| Log a pumping session in ml |
| Recent pumping sessions |
| Delete a pumping session by ID |
| Add a free-text note |
| Recent notes |
| Delete a note by ID |
| List active timers |
| Start a new timer |
| Stop/delete a timer |
| List all tags |
| All events for a child on a given day |
Deploying to Google Cloud Run
The included Dockerfile targets Cloud Run.
Deploy to GCP
gcloud run deploy babybuddy-mcp \
--source=. \
--allow-unauthenticated \
--set-env-vars="BABYBUDDY_INSTANCE=$BABYBUDDY_INSTANCE,BABYBUDDY_TOKEN=$BABYBUDDY_TOKEN"Testing
To run the end-to-end tests against your real BabyBuddy instance:
Ensure your
.envfile hasBABYBUDDY_INSTANCEandBABYBUDDY_TOKENset.Install test dependencies:
uv pip install -r requirements.txtRun the tests:
uv run pytest tests/test_e2e.py
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/amirkaromashkin/babybuddy-mcp'
If you have feedback or need assistance with the MCP directory API, please join our Discord server