A
licenseA
qualityA
maintenanceAn MCP server that allows users to query and analyze their Apple Health data using SQL and natural language, utilizing DuckDB for fast and efficient health data analysis.
3
91 npm
574
MIT
MetricBridge (formerly Health Export AI)
by PhilipAD
Related Servers
Alternatives to MetricBridge (formerly Health Export AI)
No user-submitted related servers found.
Related Servers
- FlicenseNot gradedqualityBmaintenanceMCP server that enables LLMs to query Apple Health data such as steps, heart rate, sleep, and workouts via natural language, with secure cloud access through OAuth.1-
- AlicenseAqualityDmaintenanceA Model Context Protocol server that enables seamless interaction between LLM-based agents and Apple Health data, allowing users to query, analyze, and manage health records through natural language commands.7286MIT
- AlicenseAqualityAmaintenanceRead-only MCP server that exposes Apple Health data (steps, workouts, sleep, etc.) from a local SQLite store, allowing AI agents to query health metrics without sending data to hosted services.932Apache 2.0
- AlicenseNot gradedqualityNot gradedmaintenanceAn MCP server that gives AI read-only access to Apple Health data through shortcuts and Cloudflare, enabling queries of current stats, detailed records, and trends.MIT
- AlicenseNot gradedqualityCmaintenanceA remote MCP server that lets AI assistants such as Claude, ChatGPT, and any MCP client ask about a user's Apple Health data, with answers produced live by the user's iPhone via HealthKit. Health data is forwarded through process memory only — never written to disk — and covers sleep, workouts, metric series, health overviews, and user-defined custom metrics.AGPL 3.0
TDQS
A4/5.0
Scored across 22 tools
Disambiguation3/5
Several clusters overlap: get_health_metrics, get_structured_export, and query_health_data all retrieve metric values, and get_trends, compare_periods, and correlate_metrics all do comparison/analysis. The very detailed descriptions do spell out when to prefer each (e.g. intraday vs day-level, NL vs specific tools), so an agent can mostly recover, but the boundaries are not self-evident from names alone.
Naming Consistency5/5
Nearly every tool follows a clean verb_noun pattern: get_workouts, list_metrics, correlate_metrics, add_event, remove_event, compare_periods, resolve_metric, query_health_data. The verb choices (get/list/query) are used consistently and predictably across the whole set.
Tool Count4/5
22 tools is on the heavy side, but each maps to a distinct data surface (workouts, sleep, cycle, check-ins, strength, labs, tags, intraday, events, profile, plus status/freshness). The count is justified by the breadth of exported files rather than redundant tooling.
Completeness4/5
The surface covers discovery (list_metrics, resolve_metric), retrieval across day/hour/structured views, analysis (trends, compare, correlate), freshness/status, and event lifecycle (list/add/remove). Minor gaps: no update_event (must remove and re-add) and writes are limited to agent events by design, but core workflows have no dead ends.
Maintenance
ActivityActive
ResponsivenessOutdated data