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.
2
3
491
564
MIT
Quantified Self MCP Server
by Thecimal
This server gives LLMs private, local access to personal health data stored in SQLite via MCP.
Read health metrics: daily steps, sleep hours, resting heart rate, weight, workout minutes, mood, and water intake for a date range.
Log daily metrics: record any of those metrics for a specific day without clearing other values; per-date upsert only, no arbitrary SQL.
Local-first privacy: data stays in local SQLite and the server runs on your machine; works with local or cloud MCP-compatible LLMs.
Flexible data: optional metric fields, automatic DB migration, and CSV import/upsert via
init_db.py.
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., "@Quantified Self MCP ServerWhat was my average sleep and steps last week?"
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.
Quantified Self MCP
Try it Live!
A private, local-first MCP server that lets LLMs access your personal health data.
Quantified Self MCP connects an LLM to health data stored on your computer using the Model Context Protocol (MCP).
It is not limited to Claude. It can work with local LLMs as well as cloud-based models that support MCP.
Privacy first
Your health data is stored locally in SQLite, and the MCP server runs entirely on your computer.
Your Health Data
↓
Local SQLite
↓
MCP Server
↓
LLMFor maximum privacy, use a local LLM so everything stays on your machine.
Cloud LLMs such as Claude can also be used. In that case, your database and MCP server remain local, but the data returned to the model may be sent to the cloud provider.
Related MCP server: apple-health-mcp
Current functionality
The server currently provides three tools:
read_health_data — read-only
It can access:
Daily steps
Sleep duration
Resting heart rate
Weight (kg)
Workout minutes
Mood (1–10 scale)
Water intake (ml)
Data for a selected date range
Every field is optional per day — log just the metrics you actually track.
log_daily_metric — write
Lets the LLM record any of the metrics above for a given day, without you touching a CSV or SQLite directly. Pass just the fields you're logging (e.g. only mood) and the rest of that day's data is left exactly as it was — nothing is ever cleared, only set. Values are checked against generous sanity bounds before being written (e.g. mood 1–10, resting_heart_rate 20–250 bpm) — this catches unit mix-ups and typos, not "abnormal" readings. It's a plain per-date upsert into daily_metrics; there's no way for it (or anything else in this server) to run arbitrary SQL. The same bounds are applied to CSV imports via init_db.py, so a bad value there is skipped with a warning rather than silently loaded.
clear_metric — write
Blanks out a single metric for a single day, for undoing a bad log_daily_metric call (wrong date, wrong units, etc.) without needing to re-run init_db.py.
Installation
git clone https://github.com/Thecimal/quantified-self-mcp.git
cd quantified-self-mcp
python3 -m venv .venv
source .venv/bin/activate
pip install -r requirements.txtInitialize the database:
python init_db.py sample_data/health_sample.csvCSV columns: date, steps, sleep_hours, resting_heart_rate are required;
weight_kg, workout_minutes, mood, water_ml are optional — include any
subset of them. Re-running init_db.py upserts by date, and a CSV that
omits an optional column leaves that column's existing values alone
rather than clearing them, so you can add a new metric later without
disturbing what's already logged. An existing database is migrated
automatically, so upgrading never requires deleting it.
Using it with LLMs
Use it with any MCP-compatible client and model — local LLMs, Claude, or anything else that speaks MCP.
Claude Desktop
One command, using the included fastmcp.json:
fastmcp install claude-desktopThis registers the server in Claude Desktop's config, and has uv manage an isolated environment with this project's dependencies (no need to have already run pip install -r requirements.txt first) — restart Claude Desktop afterwards and look for the 🔨 icon to confirm it loaded.
Other MCP clients (Cursor, Claude Code, Gemini CLI, etc.)
fastmcp install cursor # or: claude-code, gemini-cli, gooseAny client not directly supported by fastmcp install can still use standard MCP JSON config, generated the same way:
fastmcp install mcp-json fastmcp.jsonPaste the output into that client's config file under its mcpServers key.
Try it
How has my sleep changed over the last 30 days?
The LLM retrieves the relevant data through MCP and analyzes it.
Project structure
server.py # MCP server
logic.py # Data validation and analysis
init_db.py # Database initialization
sample_data/ # Example health data
fastmcp.json # One-command install into Claude Desktop/Cursor/etc.Limitations
Single machine only, by design. The database is a plain SQLite file on disk — there's no sync, no server component, no accounts. That's the same choice that keeps your data private: nothing here is built to talk to a network. If you use this on more than one computer, each one has its own independent data/health.db; nothing here merges them. Copying the file yourself (e.g. via a synced folder) works but isn't something this project manages or is tested against.
Philosophy
Your data stays yours.
Keep your personal data local, give the LLM controlled access, and choose whether the model runs locally or in the cloud.
License
MIT
Available Tools
3 toolsclear_metricA
Blank out (set to null) a single metric for a single day, without touching that day's other metrics. The counterpart to log_daily_metric for undoing a bad value — e.g. a mood logged for the wrong day, or a weight entered with the wrong units.
ParametersJSON Schema
| Name | Required | Description | Default |
|---|---|---|---|
| date | Yes | The day to clear a field for, formatted YYYY-MM-DD. | |
| field | Yes | Which metric to blank out. One of: steps, sleep_hours, resting_heart_rate, weight_kg, workout_minutes, mood, water_ml. |
Output Schema
ParametersJSON Schema
| Name | Required | Description |
|---|---|---|
| result | Yes |
TDQS
A4.5/5.0
Behavior4/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries the behavioral disclosure burden. It clearly communicates the mutation ('blank out'), the exact scope (one metric, one day), and the guarantee that other metrics are untouched. It could add permanence or no-op behavior details, but the core destructive semantics are clear.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness5/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is compact and front-loaded with the action and scope. The examples are meaningful and help clarify intent without wasted words.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness5/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a two-parameter tool with full schema coverage and an output schema, the description covers the operation's purpose, scope, and usage context. Nothing essential is missing for correct invocation.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters3/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 100%, so the input schema already documents date formatting and the allowed field values. The description adds contextual examples but no new parameter-level semantic detail, so the baseline of 3 is appropriate.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description uses a specific verb ('Blank out (set to null)') and names the exact resource: a single metric for a single day. It also explicitly distinguishes itself from log_daily_metric, making the tool's purpose unambiguous.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines5/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
It explicitly frames this tool as the counterpart to log_daily_metric for undoing bad values, with concrete examples. This gives clear when-to-use guidance and implies the alternative for normal metric logging.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
log_daily_metricA
Record one or more health metrics for a single day, creating that day's row if it doesn't already have one.
Only the metrics you pass are written — anything left as null is not touched, so logging just today's mood doesn't erase today's steps if they were set earlier. To undo a value logged by mistake, use clear_metric rather than trying to overwrite it with a placeholder.
ParametersJSON Schema
| Name | Required | Description | Default |
|---|---|---|---|
| date | Yes | The day to log, formatted YYYY-MM-DD. | |
| mood | No | Mood rating on a 1-10 scale. | |
| steps | No | Step count for the day. 0-200,000. | |
| water_ml | No | Water intake in millilitres. 0-10,000. | |
| weight_kg | No | Body weight in kilograms. 1-500. | |
| sleep_hours | No | Hours of sleep. 0-24. | |
| workout_minutes | No | Minutes of exercise. 0-1,440. | |
| resting_heart_rate | No | Resting heart rate in bpm. 20-250. |
Output Schema
ParametersJSON Schema
| Name | Required | Description |
|---|---|---|
| result | Yes |
TDQS
A4.9/5.0
Behavior5/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description carries the full behavioral burden and succeeds: it discloses row creation, partial-write semantics, and the fact that nulls are untouched. This is exactly the kind of behavioral context an agent needs before calling a mutating tool.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness5/5
Is the description appropriately sized, front-loaded, and free of redundancy?
Three sentences with no filler. The core purpose is front-loaded, and every sentence contributes either behavioral semantics or usage guidance. The description is compact yet rich.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness5/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
The tool has an output schema (per context), so return-value prose is unnecessary. The description covers creation, partial updates, null behavior, and the correct sibling for undo. Nothing an agent needs to call this correctly is missing.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters4/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 100%, giving the baseline 3, but the description adds meaningful parameter behavior beyond the schema: only passed metrics are written, nulls are not touched, and at least one metric is implied. This improves the agent's understanding of how the nullable parameters actually behave.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description opens with a specific verb and resource: 'Record one or more health metrics for a single day.' It also distinguishes itself from siblings by explicitly naming clear_metric for undo operations, so an agent can tell logging from reading or clearing without ambiguity.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines5/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
It clearly states when to use the tool (logging metrics for a day) and when not to ('To undo a value logged by mistake, use clear_metric'). It also explains the partial-update behavior, which prevents agents from thinking they must re-send all values.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
read_health_dataA
Read daily health metrics from the local database: steps, sleep hours, resting heart rate, weight (kg), workout minutes, mood, and water intake (ml).
ParametersJSON Schema
| Name | Required | Description | Default |
|---|---|---|---|
| end_date | No | Last day to include, formatted YYYY-MM-DD. Defaults to today. | |
| start_date | No | First day to include, formatted YYYY-MM-DD. Defaults to 30 days before end_date. Ranges over ~10 years are rejected. |
Output Schema
ParametersJSON Schema
| Name | Required | Description |
|---|---|---|
| result | Yes |
TDQS
A3.6/5.0
Behavior3/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description must carry the burden. It clearly indicates the operation is a read from a local database, implying no mutation, and enumerates the data domains. It does not disclose potential behaviors like pagination, empty-result handling, or timezone assumptions, but output schema plus 'read' cover the essential safety profile.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness5/5
Is the description appropriately sized, front-loaded, and free of redundancy?
A single, front-loaded sentence states the operation, source, and the complete list of metrics with units. There is no filler or repetition of schema details.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness4/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a read tool with no required parameters, a rich input schema, and an output schema, the description is nearly complete: it identifies the source and the returned metric categories. The main missing piece is explicit routing guidance versus siblings, which was already penalized under usage guidelines.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters3/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 100% and the start_date/end_date parameters have detailed descriptions including format, defaults, and the ~10-year restriction. The tool description itself adds no parameter-level information, so the baseline of 3 applies.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description uses the specific verb 'Read' with a clear resource, 'daily health metrics from the local database', and lists the exact metrics included. This differentiates it from the write/delete siblings log_daily_metric and clear_metric.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description gives no explicit guidance on when to choose this tool over its siblings, such as 'use for retrieving metrics as opposed to logging or clearing them.' Although the name implies a read operation, no when-to-use or exclusion criteria are stated.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections. Dates show when Glama detected each change.
2 tool updates
v1.0.4- Added
clear_metric - Added
log_daily_metric
2 tool updates
v1.0.3- Removed
read_finance_data - Changed
read_health_data1 field changed- changed
Input schema / properties / start_date / descriptionPrevious value: -"First day to include, formatted YYYY-MM-DD.\n Defaults to 30 days before end_date."New value: +"First day to include, formatted YYYY-MM-DD.\nDefaults to 30 days before end_date. Ranges over ~10 years are rejected."
1 tool update
v1.0.1- Changed
read_finance_data1 field changed- changed
Input schema / properties / category / descriptionPrevious value: -"Optional category name to filter to (case-insensitive,\n exact match — e.g. \"Groceries\"). Omit to include all categories."New value: +"Optional category name to filter to (case-insensitive,\n exact match — e.g. \"Groceries\"). A category with no matching\n rows returns an empty \"transactions\" list, not an error — this\n usually means a typo or a category that isn't in the ledger.\n Omit to include all categories."
2 tool updates
v1.0.0- First observed
read_finance_data - First observed
read_health_data
TDQS
A4.1/5.0
Disambiguation5/5
Each tool maps to a distinct operation: reading, logging, and clearing metrics. There is no overlap or ambiguity between them.
Naming Consistency4/5
All tool names are snake_case and follow a verb-first pattern. The object names vary slightly ('health_data' vs 'daily_metric' vs 'metric'), but the intent remains clear.
Tool Count5/5
Three tools is well-scoped for a simple quantified-self server: read, log, and clear. Each tool serves a necessary purpose without redundancy.
Completeness4/5
Core workflow coverage is solid: read metrics, write metrics, and undo mistakes. Minor gaps exist, such as no way to delete an entire day or list supported metric types, but these are workable limitations.
Maintenance
ActivityMaintained
ResponsivenessNo issues
Related MCP Connectors
Personal finance, bank account, and shared memory connector for Claude, ChatGPT, Gemini Spark & more
Query 40 databases from Claude, ChatGPT, or Cursor — on any device. Read-only, encrypted, audited.
Your personal data for AI — Telegram, bank, courses, Zoom & more, scoped to you.
Ask data questions in natural language. Get SQL, insights, and charts from your databases.
Related MCP Servers
- AlicenseNot gradedqualityCmaintenanceLoads Apple Health export data into a local SQLite database and exposes tools to query health metrics and workout records via natural language.3MIT
- AlicenseNot gradedqualityCmaintenanceTurns a personal-finance SQLite database into typed, schema-validated tools that an AI assistant can call directly, letting you manage accounts, transactions, budgets, debts, investments, tax estimates, and goals through natural language.47MIT
- AlicenseNot gradedqualityDmaintenanceEnables querying personal data synced from services like Lunch Money and Strava using SQL via Claude.151MIT
Latest Blog Posts
- Who's Calling? MCP Hosts Are an Identity Blind Spot (And the Spec Knows It)By Om-Shree-0709 on .mcpAgent IdentityOAuth 2.1
- 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/Thecimal/quantified-self-mcp'
If you have feedback or need assistance with the MCP directory API, please join our Discord server