# Health XML Export Parser MCP > The Health XML Export Parser handles huge Apple Health or Google Fit XML files safely. Stop giving your AI client massive, unmanageable data dumps that crash its context window. This MCP locally parses multi-megabyte health exports, aggregating millions of records (like step counts and heart rates) into structured summaries the AI can actually read. ## Overview - **Category:** data-analytics - **Price:** Free - **Tags:** xml-parsing, health-data, data-processing, fitness-tracking, data-extraction ## Description Trying to feed an entire year's worth of biometric data—think hundreds of megabytes—into a chat interface is a recipe for failure. Your AI client will crash before it even gets past the raw text dump. This MCP solves that problem by running a high-performance parser locally on your machine. Instead of sending millions of individual lines to your agent, it intelligently analyzes the file's structure and aggregates the data. It tells the AI exactly what types of records exist—like StepCount or SleepAnalysis—and provides total counts along with safe samples for deeper inspection. This whole process keeps all sensitive health data private because it never leaves your local machine. When you connect this MCP through Vinkius, you get reliable access to powerful data processing without any context window limits. ## Tools ### parse_health_export Provide the file path to parse Apple Health or Google Fit XML exports, aggregating data to prevent context overflow. ## Prompt Examples **Prompt:** ``` Scan my Apple Health export.xml and tell me what types of metrics are tracked. ``` **Response:** ``` Your export contains exactly 1,240,000 StepCounts, 500,123 HeartRates, and 450 SleepAnalysis records. Which one should we analyze first? ``` **Prompt:** ``` Look at my health export and summarize my device sources. ``` **Response:** ``` The data is primarily sourced from an 'Apple Watch Series 8' and an 'iPhone 14 Pro'. ``` **Prompt:** ``` Based on the sample data of 'SleepAnalysis', what format does Apple use to track sleep? ``` **Response:** ``` Apple tracks sleep using a StartDate, EndDate, and a 'value' string representing the sleep state (e.g., Core, REM, Deep). ``` ## Capabilities ### Analyze raw export files You provide the file path and the tool parses massive Apple Health or Google Fit XML exports safely. ## Use Cases ### Figuring out overall metrics captured A user wants to know if their Apple Health export includes sleep stage details. They run the `parse_health_export` tool and ask their agent, 'What types of records are present?' The agent immediately replies with a list of all available metric types (e.g., HeartRate, SleepAnalysis), giving them an instant inventory. ### Comparing data sources A consultant needs to know if client data comes from the watch or the phone. They use `parse_health_export` on a mixed export and ask their agent to summarize the primary device identifiers, allowing them to quickly diagnose potential syncing issues. ### Setting up long-term tracking reports A researcher needs to build a longitudinal study. Instead of manually processing 10 different years of XML files, they run `parse_health_export` on each one and have their agent aggregate the total counts for core metrics across all datasets. ### Testing data completeness A user suspects a gap in their recorded activity. They use `parse_health_export` and ask their agent to list all record types, immediately seeing that 'RunningDistance' is zero, confirming they forgot to sync certain activities. ## Benefits - Handles multi-megabyte files without crashing. You can feed the tool an entire year of data, and your agent won't lose context on record count or structure. - Saves you from manual parsing. Instead of having to copy/paste millions of lines into a spreadsheet just for a summary, you let the MCP aggregate the raw numbers automatically. - Maintains total privacy. Since this process happens entirely locally on your machine, sensitive health data never leaves your device or is exposed to external services. - Provides immediate structural context. You don't just get a blob of text; the tool tells your agent exactly what kinds of metrics exist (like SleepAnalysis) and how many records there are. - Makes advanced analysis possible. You can ask your AI client complex questions about data structure, like determining which devices were responsible for the bulk of step counts. ## How It Works The bottom line is you get structured, manageable data summaries from enormous health files, letting your AI client actually use the information instead of getting overloaded by it. 1. Provide the absolute file path to your exported health data (e.g., export.xml). 2. The MCP uses a local, high-performance parser to ingest the massive XML file without overwhelming your AI client's context. 3. You receive an aggregated summary that tells your agent exactly which types of metrics exist and how many records there are. ## Frequently Asked Questions **Can I use Health XML Export Parser for Google Fit files?** Yes, this MCP is designed to handle both Apple Health and Google Fit XML exports. You simply provide the file path, and the parser handles the specific structure of either export type. **Does using parse_health_export affect my data privacy?** No. The parsing happens entirely on your local machine. Your sensitive health metrics are never uploaded or stored anywhere outside of your controlled environment. **What is the maximum size file that parse_health_export can handle?** It is built for multi-megabyte files, designed specifically to prevent context window overflow. It aggregates data intelligently rather than transmitting the full raw text. **Does this MCP help me analyze step counts or heart rates?** Yes, it first identifies that those metrics exist and provides their total count. Your agent then uses that structured summary to run detailed analysis on them. **Do I need to write any code to use Health XML Export Parser?** No. You just interact with the tool by providing the file path, and your AI client handles the rest of the data processing automatically.