A
licenseA
qualityA
maintenanceIntegrates Diabetes:M data with Claude Desktop to access glucose readings, insulin data, food diary, and health metrics through natural language conversations.
11
MIT
SuperGlookoQuery
by sikcapri
Related Servers
Alternatives to SuperGlookoQuery
- AlicenseAqualityDmaintenanceEnables Claude Desktop to securely access FreeStyle LibreLink continuous glucose monitoring data, providing real-time readings, historical analysis, and health insights through natural language queries.815MIT
- AlicenseAqualityAmaintenanceEnables Claude Desktop to query and analyze diabetes data from Omnipod 5 and Glooko through natural language, providing clinical audit and triage insights such as time in range, trends, and bolus analysis.12MIT
Related Servers
- AlicenseAqualityAmaintenanceEnables access to FreeStyle Libre glucose data through Claude Desktop, providing current readings, historical data, statistics, and trend analysis from LibreLinkUp accounts with secure credential storage.101MIT
- AlicenseAqualityCmaintenanceEnables Claude to access Abbott Freestyle Libre CGM data from multiple providers (LibreView, Terra, Thryve) to retrieve current glucose, history, and summaries via natural language.42MIT
- AlicenseNot gradedqualityBmaintenanceA Model Context Protocol (MCP) server that connects Claude to your personal Dexcom CGM (Continuous Glucose Monitor) for assistive diabetes management intelligence.MIT
- AlicenseAqualityDmaintenanceBridges your Nightscout CGM data with AI assistants via the Model Context Protocol, enabling natural language queries about glucose readings, treatments, statistics, and pattern analysis.21GPL 3.0
- FlicenseNot gradedqualityNot gradedmaintenanceEnables querying Dexcom Stelo glucose data by importing Clarity CSV exports into SQLite and providing MCP endpoints for glucose readings, statistics, and time-in-range analysis.-
- AlicenseNot gradedqualityBmaintenanceGives Claude and other MCP clients read-only access to Oura Ring data through the Oura API v2, exposing sleep sessions, readiness, activity, stress, heart rate, workouts and long-range trends as queryable tools. It runs locally, evens out the API's quirks, and keeps credentials on the user's machine.MIT
TDQS
A4.4/5.0
Scored across 16 tools
Disambiguation4/5
Most tools have clearly distinct purposes, and descriptions aggressively cross-reference each other to prevent misselection (e.g., get_chart_series vs get_chart_html, get_daily_insulin vs get_diabetes_summary). However, get_chart_series/get_chart_html and get_diabetes_summary/get_trend are close enough that a skimming agent could still pick the wrong one without reading carefully.
Naming Consistency5/5
Every tool follows a consistent verb_noun snake_case pattern: 13 of 16 begin with get_, and the exceptions (submit_registry_contribution, activate_clinical_auditor_persona) use the same verb_noun convention with different verbs. No camelCase or mixed style anywhere; the noun always identifies the resource or output format.
Tool Count4/5
At 16 tools the server is one over the typical 3-15 sweet spot, but each tool covers a distinct data view (glucose, insulin, settings, device events, charts, meal windows) plus a two-step registry workflow. The breadth of the diabetes domain justifies the count, though the registry-contribution and persona tools are somewhat orthogonal to the core querying purpose.
Completeness4/5
For a read-only analysis server, coverage is thorough: raw glucose, chart data, rendered charts, multi-period and hourly aggregates, bolus logs (enriched and split), daily insulin, basal states, settings history, device events, and meal-window analysis. Minor gaps exist — no dedicated carb-entry log, activity/notes data, or patient-profile tool — but nothing that creates a dead end for common workflow.
Maintenance
ActivityMaintained
ResponsivenessNo issues