Quantified Self MCP Server
Servidor MCP de Quantified Self
Un servidor local del Model Context Protocol (MCP) que permite a un LLM — p. ej. Claude Desktop — consultar tus datos personales de salud y finanzas. Todo se almacena en dos archivos SQLite locales y se lee directamente del disco mediante un proceso de Python que tú controlas. Sin base de datos en la nube, sin panel de control, sin servicios de terceros.
Qué incluye
quantified-self-mcp/
├── server.py # the MCP server (FastMCP) — 2 tools
├── init_db.py # loads a CSV file into the local SQLite database
├── requirements.txt
├── .gitignore # keeps data/ and .db files out of version control
└── sample_data/
├── health_sample.csv # 30 days of sample data, so you can try it immediately
└── finance_sample.csv # ~2 months of sample expensesAl ejecutar init_db.py se crea una carpeta data/ junto a server.py que contiene health.db y finance.db; esa carpeta no está incluida aquí, ya que se genera en tu máquina a partir de tus propios datos.
Related MCP server: apple-health-mcp
Herramientas expuestas
Herramienta | Devuelve | Parámetros (todos opcionales) |
| Pasos diarios, horas de sueño, frecuencia cardíaca en reposo |
|
| Libro de gastos por categoría, con totales |
|
Ambas herramientas devuelven las filas coincidentes más resúmenes calculados (promedios/mín/máx para salud, totales por categoría para finanzas), de modo que el modelo no tenga que hacer su propia agregación entre muchas filas.
1. Configurar el entorno
Requiere Python 3.10+.
cd quantified-self-mcp
python3 -m venv .venv
source .venv/bin/activate # Windows: .venv\Scripts\activate
pip install -r requirements.txt2. Cargar tus datos
Pruébalo de inmediato con las muestras incluidas:
python init_db.py health sample_data/health_sample.csv
python init_db.py finance sample_data/finance_sample.csvPara usar tus propios datos, expórtalos a CSV con estas columnas y ejecuta los mismos comandos con tus archivos:
CSV de salud:
date, steps, sleep_hours, resting_heart_rateCSV de finanzas:
date, category, amount, description(descriptiones opcional)
Las fechas deben estar en formato ISO (2026-08-23); también se acepta MM/DD/AAAA y se convierte. Las cantidades/números pueden incluir $ y , (p. ej. $1.234,56) — se eliminan automáticamente. Una fila con un problema (fecha incorrecta, cantidad no numérica, categoría faltante, etc.) se omite con una advertencia en lugar de abortar toda la importación; la última línea impresa siempre te indica cuántas filas se cargaron frente a cuántas se omitieron.
Volver a ejecutar init_db.py health actualiza por fecha (es seguro re-ejecutarlo a medida que añades días); init_db.py finance añade filas nuevas cada vez, ya que un libro de gastos no tiene una clave única natural. Añade --replace a cualquiera de los dos comandos para vaciar la tabla primero.
3. (Opcional) probarlo de forma independiente
Antes de conectarlo a cualquier cliente, puedes abrir el MCP Inspector y llamar a las herramientas directamente en un navegador:
fastmcp dev inspector server.py4. Conectarlo a Claude Desktop
Claude Desktop lanza servidores MCP locales como subprocesos y se comunica con ellos a través de stdio, según un archivo de configuración JSON:
macOS:
~/Library/Application Support/Claude/claude_desktop_config.jsonWindows:
%APPDATA%\Claude\claude_desktop_config.jsonLinux:
~/.config/Claude/claude_desktop_config.json
Puedes ir directamente desde la aplicación: Ajustes → Desarrollador → Editar configuración.
Añade una entrada en mcpServers, usando rutas absolutas — es importante que command apunte al intérprete de Python dentro del entorno virtual que acabas de crear, no a un python a secas. Claude Desktop ejecuta los servidores en un entorno mínimo que no hereda de forma fiable el PATH de tu shell ni un venv activado, por lo que un "python" a secas suele resolverse al intérprete incorrecto (o a ninguno) y el servidor falla silenciosamente al iniciarse.
{
"mcpServers": {
"quantified-self": {
"command": "/absolute/path/to/quantified-self-mcp/.venv/bin/python3",
"args": ["/absolute/path/to/quantified-self-mcp/server.py"]
}
}
}En Windows, normalmente es:
{
"mcpServers": {
"quantified-self": {
"command": "C:\\absolute\\path\\to\\quantified-self-mcp\\.venv\\Scripts\\python.exe",
"args": ["C:\\absolute\\path\\to\\quantified-self-mcp\\server.py"]
}
}
}Guarda el archivo y, a continuación, cierra y vuelve a abrir Claude Desktop por completo (no basta con cerrar la ventana; es necesario reiniciar para cargar los cambios de configuración). Busca el icono de herramientas/martillo en el cuadro de chat para confirmar que quantified-self está conectado.
FastMCP también incluye un atajo CLI que edita este archivo por ti — fastmcp install claude-desktop server.py --name "Quantified Self" — merece la pena probarlo (ejecuta fastmcp install claude-desktop --help para ver las opciones actuales), pero el JSON manual anterior siempre funcionará y es más fácil de depurar si algo falla. Anthropic también tiene un formato de empaquetado más reciente de "Desktop Extension" con un solo clic para servidores MCP locales; no es necesario para un uso personal como este, pero conviene saber que existe si algún día quieres compartir este servidor con alguien menos cómodo editando JSON.
5. (Opcional) ejecutarlo en Docker / alojarlo en Glama
#5-optional-run-it-in-docker--host-it-on-glama
Se incluye un Dockerfile para quien quiera ejecutar esto en un contenedor en lugar de un venv local, incluido alojarlo en Glama, que compila directamente a partir del Dockerfile de un repositorio cuando está presente.
docker build -t quantified-self-mcp .
docker run -i --rm -v "$PWD/data:/app/data" quantified-self-mcpLa imagen es solo Python (python:3.12-slim + pip install -r requirements.txt); no hay Node.js en ningún lugar de este proyecto. HEALTH_DB_PATH y FINANCE_DB_PATH apuntan por defecto a /data/health.db y /data/finance.db dentro del contenedor, de modo que un volumen montado (p. ej. el montaje /data de Glama) conserve tus bases de datos entre redespliegues; consulta la sección de Configuración al principio de server.py para sobrescribirlos.
glama.json es intencionadamente mínimo — solo indica a Glama que use este repositorio; el Dockerfile es la fuente de verdad real sobre cómo se compila e inicia la imagen (python server.py, a través de stdio). Una versión anterior de glama.json intentaba configurar manualmente un buildpack genérico (una imagen base debian:trixie-slim desnuda más pasos de compilación manuales de pip install y cmdArguments) en lugar de usar un Dockerfile — esa imagen no tenía un intérprete de Python aprovisionado de forma fiable, y la plataforma acababa intentando ejecutar un punto de entrada de Node.js que no existe en este repositorio (Cannot find module '/app/server.js'). Incluir un Dockerfile elimina esa ambigüedad.
Modelo de privacidad — qué significa realmente "local"
Conviene ser precisos al respecto, ya que es el objetivo principal del proyecto:
Ambas bases de datos SQLite viven solo en tu disco, dentro de la carpeta
data/de este proyecto. El servidor no realiza llamadas de red, no tiene telemetría y no sincroniza nada en ningún sitio.server.pyabre ambas bases de datos en modo de solo lectura de SQLite (no es solo que "no emita escrituras" — la conexión es físicamente incapaz de hacerlo). Ni siquiera un prompt con errores o malintencionado puede conseguir que ninguna de las dos herramientas modifique tus datos; soloinit_db.py, ejecutado por ti desde la terminal, escribe en ellas.Cuando un cliente MCP llama a una de estas herramientas, las filas específicas devueltas para esa consulta pasan a formar parte de la conversación enviada al modelo que responda — ese es el mecanismo que usa MCP para dar información a un modelo. Si usas Claude Desktop con un modelo alojado, eso significa que la porción de datos sobre la que preguntes se envía a Anthropic para ese turno, igual que cualquier otra cosa que escribas en el chat.
Así que "local" aquí significa: tu conjunto de datos completo nunca se almacena ni se sincroniza en ninguna base de datos de terceros, y no se transmite nada a menos que se invoque realmente una herramienta — y, aun así, solo las filas que devuelve esa llamada concreta, no toda la base de datos. No significa totalmente sin conexión de extremo a extremo. Para eso necesitarías un runtime de modelo totalmente local (p. ej. Ollama) junto con un cliente compatible con MCP.
Solución de problemas
El servidor no aparece en Claude Desktop: comprueba que
commandyargsusan rutas absolutas, confirma que la ruta de Python del venv existe realmente y confirma que cerraste y volviste a abrir la aplicación por completo. Los registros están en~/Library/Logs/Claude(macOS) o%APPDATA%\Claude\logs(Windows) —mcp-server-quantified-self.logmostrará el stderr de este servidor específicamente."No health/finance database found" desde una herramienta: ejecuta primero
init_db.pypara ese conjunto de datos — las herramientas no crean bases de datos vacías automáticamente a propósito, para que no obtengas respuestas vacías en silencio.Los cambios en
server.pyno parecen surtir efecto: reinicia Claude Desktop; inicia el proceso del servidor una vez por sesión de la aplicación, no por mensaje.El alojamiento en Glama falla con
Cannot find module '/app/server.js': esto significa que el despliegue recurrió a un runtime de Node.js en lugar de Python — este repositorio no tieneserver.js. Compila a partir delDockerfileincluido (consulta "Ejecutarlo en Docker / alojarlo en Glama" más arriba) en lugar de una configuración de buildpack genérica, para que la plataforma ejecutepython server.pyde forma fiable.
Ampliar esto
Algunos pasos siguientes naturales, si los quieres — nada de esto está construido, solo es hacia donde lleva el patrón:
Escribir herramientas (
log_expense,log_daily_metric) para que las entradas se puedan añadir a través del LLM en lugar de mediante CSV/SQL directamente.Más métricas — peso, entrenamientos, estado de ánimo, ingesta de agua — cada una es solo otra tabla y otra herramienta de lectura.
Una herramienta de presupuesto frente a real que compare los totales de
read_finance_datacon los objetivos que definas.
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.
| 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
| Name | Required | Description |
|---|---|---|
| result | Yes |
TDQS
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.
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.
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.
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.
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.
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.
| 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
| Name | Required | Description |
|---|---|---|
| result | Yes |
TDQS
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.
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.
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.
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.
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.
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).
| 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
| Name | Required | Description |
|---|---|---|
| result | Yes |
TDQS
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.
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.
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.
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.
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.
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
Each tool maps to a distinct operation: reading, logging, and clearing metrics. There is no overlap or ambiguity between them.
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.
Three tools is well-scoped for a simple quantified-self server: read, log, and clear. Each tool serves a necessary purpose without redundancy.
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
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
- AlicenseAqualityAmaintenanceAn 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.23491564MIT
- 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