Server data from the Official MCP Registry
Log glucose, meals, exercise and sleep in your GlucoBeat diary by chat, and look up your own data
About
Log glucose, meals, exercise and sleep in your GlucoBeat diary by chat, and look up your own data
Remote endpoints: streamable-http: https://mcp.glucobeat.com
Security Report
Valid MCP server (1 strong, 1 medium validity signals). No known CVEs in dependencies. Imported from the Official MCP Registry.
Endpoint verified · Requires authentication · 1 issue found
Security scores are indicators to help you make informed decisions, not guarantees. Always review permissions before connecting any MCP server.
Permissions Found in Source Code
Found by scanning the linked source code. This listing connects to a hosted endpoint, so none of this runs on your machine: it describes what the server software does where it is hosted.
How to Connect
Remote Plugin
No local installation needed. Your AI client connects to the remote endpoint directly.
Add this to your MCP configuration to connect:
{
"mcpServers": {
"com-glucobeat-glucobeat": {
"url": "https://mcp.glucobeat.com"
}
}
}Documentation
View on GitHubFrom the project's GitHub README.
GlucoBeat MCP server
Log glucose, meals, exercise, insulin, medication and sleep in your GlucoBeat diary just by telling your AI assistant, and ask about what happened in your own data.
GlucoBeat is a personal glucose diary that puts your sensor readings (FreeStyle Libre, Dexcom) next to your meals, exercise, insulin, medication and sleep, and measures what happened after each event. This hosted MCP server connects it to Claude, ChatGPT, Cursor and other MCP clients.
This repository holds documentation only. The server is hosted; there is nothing to install.
| Endpoint | https://mcp.glucobeat.com (Streamable HTTP) |
| Authentication | OAuth 2.1 (authorization code + PKCE, dynamic client registration). Scopes read and log |
| Account | A GlucoBeat account. Logging and the last 3 days are free; full queries over your whole history are Premium, with 10 days to try them |
| Official MCP Registry | com.glucobeat/glucobeat |
| Docs | https://www.glucobeat.com/en/ai-assistants/ |
| Privacy | https://www.glucobeat.com/en/legal/privacy/ |
| Terms | https://www.glucobeat.com/en/legal/terms/ |
| Contact | glucobeat@wandary.com |
Tools
Log (scope log). Retries never duplicate entries.
| Tool | What it does |
|---|---|
log_glucose | A glucose reading the user measured, in the account's unit unless another is given |
log_meal | Something the user ate or drank, in their words, with carbs if given |
log_exercise / finish_exercise | An activity, finished or in progress, and its end |
log_insulin | Insulin the user says they took. It records only what the user reports; it never suggests or calculates doses |
log_medication | A medication the user says they took |
log_hypo_treatment | What the user took to treat a low |
log_sleep | Going to bed or waking up |
log_note | A free note |
delete_entry | Delete an entry by its id |
Read (scope read)
| Tool | What it does |
|---|---|
get_profile | Unit, target range, time zone and what the plan allows to read |
get_glucose | Readings of a period |
get_entries | Meals, exercise, insulin, medication, sleep and notes of a period |
get_stats | Time in range, mean, variability, episodes, by time of day and weekday/weekend |
get_meal_response | The usual response to a meal logged before: median, range, number of times and confidence |
get_entry_effect | How glucose moved after one entry |
get_exercise_summary | Days with exercise versus days without |
Everything is described as what happened in your own data, always with n and ranges. GlucoBeat is not a medical device: it never predicts, diagnoses, or gives or adjusts doses. For medical decisions, talk to your healthcare team.
Connect
Claude: GlucoBeat is in the Claude connectors directory. Or Settings → Connectors → Add custom connector → https://mcp.glucobeat.com.
ChatGPT: add it as a custom app/connector with the URL https://mcp.glucobeat.com and OAuth.
Cursor, VS Code and other clients (mcp.json):
{
"mcpServers": {
"glucobeat": {
"type": "http",
"url": "https://mcp.glucobeat.com"
}
}
}
Gemini CLI: gemini extensions install https://github.com/dmbejar/glucobeat-mcp, then /mcp auth glucobeat to sign in.
Antigravity: agy plugin install https://github.com/dmbejar/glucobeat-mcp. It opens the sign-in when it first connects.
When you connect, you sign in to GlucoBeat and give your consent on its consent screen. You can see which assistants are connected and disconnect them at any time from GlucoBeat.
Example questions
- I just measured 120
- I ran 8 km in 45 minutes
- How does my glucose usually respond to oatmeal?
- What was my time in range last week?
Privacy
Your data is stored in the EU (AWS), encrypted in transit and at rest. GlucoBeat uses no AI of its own for this: the assistant understands the request and GlucoBeat stores or returns the data. Full policy: https://www.glucobeat.com/en/legal/privacy/
server.json is the entry published in the official MCP Registry. gemini-extension.json is the Gemini CLI extension, and plugin.json with mcp_config.json is the Antigravity plugin.
Made by Wandary in Spain.
Reviews
No reviews yet
Be the first to review this server!
More Developer Tools MCP Servers
Rea
Freeby Morluto · Developer Tools
Reverse engineer anything from your terminal or agent with one CLI and MCP server.
Paperclip
Freeby Paperclipai · Developer Tools
Trending hip-hop artist momentum scores across four cultural dimensions.
Scrapling
Freeby D4Vinci · Developer Tools
Web scraping with stealth HTTP, real browsers, and Cloudflare bypass. CSS selectors supported.
Git
Freeby Modelcontextprotocol · Developer Tools
Read, search, and manipulate Git repositories programmatically
Toleno
Freeby Toleno · Developer Tools
Toleno Network MCP Server — Manage your Toleno mining account with Claude AI using natural language.
MCP Marketplace
Freeby mcp-marketplace · Developer Tools
Search and install MCP servers from inside your AI client.
