de en es ja ko ru zh

OmniFocus-MCP

Name: OmniFocus-MCP
Author: themotionmachine

by themotionmachine

Overview Schema Source Related Servers Discussions Admin

TypeScript

Local

Servidor MCP de OmniFocus

npm version

Un servidor de Protocolo de Contexto de Modelo (MCP) que conecta OmniFocus con Claude y otros asistentes de IA compatibles con MCP.

Resumen

Este servidor une a los asistentes de IA con tu base de datos de OmniFocus. Mediante conversación natural, un asistente puede consultar, crear, editar y eliminar tareas y proyectos, incluidas operaciones masivas. Algunas cosas que puedes hacer con él:

Convertir un PDF de un programa de estudios en un proyecto completamente especificado con tareas, etiquetas, fechas de aplazamiento y fechas de vencimiento
Convertir la transcripción de una reunión en una lista de acciones
Auditar y reorganizar tus etiquetas, proyectos y carpetas de forma conversacional
Crear visualizaciones de tus tareas, proyectos y etiquetas
Procesar docenas de elementos en una sola operación por lotes

Related MCP server: MCP OmniFocus

Inicio rápido

Requisitos previos

macOS con OmniFocus instalado
Node.js 20 o posterior (para npx)

La primera vez que el servidor hable con OmniFocus, macOS te pedirá que permitas el acceso de automatización. Concédelo una vez y listo.

Claude Desktop

Añade el servidor a ~/Library/Application Support/Claude/claude_desktop_config.json:

{
  "mcpServers": {
    "omnifocus": {
      "command": "npx",
      "args": ["-y", "omnifocus-mcp"]
    }
  }
}

Luego reinicia Claude Desktop.

Claude Code

claude mcp add omnifocus -- npx -y omnifocus-mcp

Otros clientes MCP funcionan de la misma manera: ejecuta npx -y omnifocus-mcp a través de stdio.

Ejemplos de conversación

Consultas específicas:

"Muéstrame todas mis tareas marcadas con bandera que vencen esta semana"
"¿Cuáles son mis próximas acciones en la carpeta Trabajo?"
"Cuenta cuántas tareas hay en cada proyecto"

Reorganización:

"Quiero que cada tarea tenga una etiqueta de nivel de energía. Muéstrame una lista de todas las tareas que no tienen una y tus sugerencias sobre qué etiqueta añadir. Haré los cambios que considere apropiados. Luego haz los cambios en OmniFocus."

Captura desde cualquier lugar:

"Vale, gracias por la explicación detallada de por qué el estado de derecho es importante. Añade una tarea recurrente a mi proyecto de activismo que me recuerde llamar a mi representante semanalmente. Incluye un resumen de esta conversación en el campo de notas."

Trabajar con perspectivas:

"¿Qué perspectivas tengo disponibles?"
"Muéstrame lo que hay en mi perspectiva Bandeja de entrada"

Procesar transcripciones o PDFs:

"Voy a pegar la transcripción de la reunión de hoy. Por favor, analízala y crea tareas en OmniFocus para cualquier elemento de acción asignado a mí. Ponlas en mi proyecto 'Desarrollo de Producto'."

Herramientas

El servidor proporciona 12 herramientas. Los parámetros opcionales están marcados.

`query_omnifocus`

Consulta tareas, proyectos o carpetas con filtros específicos: mucho más rápido y ligero que volcar toda la base de datos. Consulta QUERY _TOOL _REFERENCE.md para la referencia completa y QUERY _TOOL _EXAMPLES.md para ejemplos prácticos.

Parámetro	Descripción
`entity`	Qué consultar: `tasks`, `projects` o `folders`
`filters` (opcional)	Combina con lógica AND; los filtros de matriz (`tags`, `status`) usan OR dentro de la matriz
`fields` (opcional)	Devuelve solo los campos enumerados: mantiene las respuestas pequeñas
`limit`, `sortBy`, `sortOrder` (opcional)	Da forma a la lista de resultados
`includeCompleted` (opcional)	Incluye elementos completados/descartados (por defecto: false)
`summary` (opcional)	Devuelve solo el recuento de coincidencias

Filtros disponibles:

Contenedores: projectName (coincidencia parcial sin distinción de mayúsculas; "inbox" apunta a la bandeja de entrada), projectId, folderId (incluye subcarpetas), folderName (coincidencia parcial sin distinción de mayúsculas, incluye subcarpetas)
Nombres: taskName (coincidencia parcial sin distinción de mayúsculas)
Etiquetas: tags (coincidencia exacta, distingue mayúsculas)
Estado: status — tareas: Next, Available, Blocked, DueSoon, Overdue, Completed, Dropped; proyectos: Active, OnHold, Done, Dropped
Fechas, orientadas al futuro: dueWithin, deferredUntil, plannedWithin (rangos), dueOn, deferOn, plannedOn (día exacto). Acepta un número de días, "today", "tomorrow", "this week", "next week" o una fecha ISO
Fechas, orientadas al pasado: addedWithin, addedOn, completedWithin, completedOn, droppedWithin, droppedOn (los filtros de completado/descartado requieren includeCompleted: true)
Marcas y varios: flagged, inbox, hasNote, isRepeating, reviewDue (solo proyectos)

`dump_database`

Obtén el estado completo de tu base de datos. Úsalo para análisis exhaustivos; prefiere query_omnifocus para cualquier consulta específica.

hideCompleted (opcional): oculta tareas completadas/descartadas (por defecto: true)
hideRecurringDuplicates (opcional): oculta instancias duplicadas de tareas recurrentes (por defecto: true)

`add_omnifocus_task`

Crea una nueva tarea.

name
projectName (opcional): proyecto al que añadir la tarea (por defecto: bandeja de entrada)
parentTaskId / parentTaskName (opcional): anidar bajo una tarea existente
note, dueDate, deferDate, plannedDate, flagged, estimatedMinutes, tags (todos opcionales)
repeat (opcional): hacerla recurrente — consulta Elementos recurrentes

`add_project`

Crea un nuevo proyecto.

name
folderName (opcional): carpeta donde colocar el proyecto
sequential (opcional): si las tareas deben completarse en orden
note, dueDate, deferDate, flagged, estimatedMinutes, tags, repeat (todos opcionales)

`edit_item`

Edita una tarea o proyecto existente. También es la forma de mover elementos: establece newProjectName para mover una tarea a un proyecto, o ""/"inbox" para enviarla a la bandeja de entrada.

id o name: qué elemento editar (el id tiene prioridad)
itemType: task o project
Comunes: newName, newNote, newDueDate, newDeferDate, newFlagged, newEstimatedMinutes (fechas en formato ISO; cadena vacía borra)
Tareas: newStatus (incomplete, completed, dropped, skipped — skipped solo para tareas recurrentes), addTags, removeTags, replaceTags, newProjectName, newPlannedDate
Proyectos: newProjectStatus (active, completed, dropped, onHold), newFolderName, newSequential, markReviewed (establece la próxima fecha de revisión según el intervalo de revisión del proyecto)
Repetición: newRepeat establece una nueva regla (misma forma que repeat al crear); newRepeat: null la borra

`remove_item`

Elimina una tarea o proyecto.

id o name: qué elemento eliminar
itemType: task o project

`batch_add_items`

Crea múltiples tareas y proyectos en una sola operación. Cada elemento acepta los mismos campos que add_omnifocus_task / add_project, más type (task o project) y ayudantes de jerarquía opcionales:

tempId: un ID temporal al que otros elementos del mismo lote pueden hacer referencia
parentTempId: anida este elemento bajo el tempId de otro elemento del lote

{
  "items": [
    { "type": "project", "name": "My Project", "tempId": "proj1" },
    { "type": "task", "name": "First task", "parentTempId": "proj1" },
    { "type": "task", "name": "Parent task", "parentTempId": "proj1", "tempId": "t1" },
    { "type": "task", "name": "Subtask", "parentTempId": "t1" }
  ]
}

`batch_remove_items`

Elimina múltiples tareas o proyectos en una sola operación. Cada elemento toma id o name, más itemType.

`list_perspectives`

Lista las perspectivas disponibles, tanto integradas como personalizadas (las perspectivas personalizadas son una función de OmniFocus Pro).

includeBuiltIn, includeCustom (opcional, por defecto: true)

`get_perspective_view`

Obtén los elementos visibles en una perspectiva con nombre.

perspectiveName: p. ej., Inbox, Flagged o un nombre de perspectiva personalizada
limit (opcional, por defecto: 100), includeMetadata (opcional), fields (opcional)

`list_tags`

Lista todas las etiquetas con su jerarquía, estado activo y recuentos de tareas.

includeDropped (opcional, por defecto: false)

`create_tag`

Crea una etiqueta, opcionalmente anidada bajo una etiqueta principal existente.

name
parentTagName / parentTagID (opcional; el ID tiene prioridad)

Elementos recurrentes

add_omnifocus_task, add_project y cada elemento en batch_add_items aceptan un objeto repeat; edit_item acepta newRepeat. Describes el horario y el servidor compila la regla de recurrencia ICS, por lo que nunca escribes una RRULE a mano.

Campo	Descripción
`method`	`start-after-completion` (cuenta desde que realmente se completa), `fixed` (cuenta desde el calendario independientemente) o `due-after-completion`
`unit`	`day`, `week`, `month` o `year`
`steps` (opcional)	Repetir cada N unidades (por defecto 1)
`weekdays` (opcional)	Días específicos, p. ej., `["MO","WE","FR"]`. Requiere `unit: "week"`

{ "name": "Weekly review", "repeat": { "method": "start-after-completion", "unit": "week" } }
{ "name": "Strength work", "repeat": { "method": "fixed", "unit": "week", "weekdays": ["TU","TH"] } }

Elige method deliberadamente — es el campo que más a menudo se configura mal a mano. Con fixed, las ocurrencias aparecen según el horario tanto si la última se completó como si no, por lo que una semana perdida deja un atraso que ponerse al día. Con start-after-completion, la próxima ocurrencia se programa desde el momento en que realmente la completas, por lo que el hábito simplemente se reanuda.

Lee una regla de vuelta con query_omnifocus usando los campos repetitionRule (cadena ICS) y repetitionMethod, o filtra con isRepeating.

Actualmente no se admiten: reglas mensuales posicionales ("tercer martes"), días específicos del mes y condiciones de fin (COUNT/UNTIL). Configúralos directamente en OmniFocus.

Recursos

Los recursos permiten a los clientes MCP adjuntar datos de OmniFocus a una conversación como contexto, sin llamadas a herramientas. En Claude Code, escribe @ para explorarlos; Claude Desktop y otros clientes que admiten recursos pueden adjuntarlos directamente. Todos los recursos devuelven JSON.

URI	Descripción
`omnifocus://inbox`	Elementos actuales de la bandeja de entrada
`omnifocus://today`	La agenda de hoy: vence hoy, planificado para hoy y atrasado
`omnifocus://flagged`	Todos los elementos marcados con bandera
`omnifocus://stats`	Estadísticas de la base de datos (recuentos de tareas, atrasadas, marcadas, etc.)
`omnifocus://project/{name}`	Tareas en un proyecto específico
`omnifocus://perspective/{name}`	Elementos visibles en una perspectiva con nombre

Los dos recursos de plantilla admiten listar todos los valores disponibles y autocompletar el parámetro {name}.

Instrucciones del servidor y registro

Instrucciones: durante el apretón de manos MCP, el servidor envía orientación de uso al cliente: consejos de selección de herramientas (prefiere query_omnifocus sobre dump_database), consejos de filtros y el catálogo de recursos. No se necesita configuración.

Registro: el servidor emite registros estructurados a través del protocolo de registro MCP. Los clientes pueden ajustar la verbosidad con logging/setLevel (debug, info, warning, error, ...). El tiempo de ejecución de los scripts y los errores se registran automáticamente.

Cómo funciona

El servidor se comunica con OmniFocus a través de osascript, usando JXA (JavaScript for Automation) y la automatización Omni integrada de OmniFocus (OmniJS) cuando corresponde. Está construido sobre el MCP TypeScript SDK oficial y se comunica con los clientes a través de stdio.

Demonio compartido

Al lanzar omnifocus-mcp se inicia un pequeño shim que se conecta a un demonio de fondo compartido, iniciando uno si aún no está en ejecución. Cada cliente en la máquina obtiene su propia sesión MCP independiente, pero todos se ejecutan dentro de ese único proceso.

Esto importa cuando varios agentes usan OmniFocus a la vez. OmniFocus es una aplicación de un solo hilo controlada mediante AppleEvents, y el servidor limita cuántas llamadas osascript ejecutará de forma concurrente. Cuando cada cliente ejecutaba su propio servidor, ese límite era por proceso: diez clientes significaban diez presupuestos independientes apuntando a una sola aplicación, lo que provocaba tiempos de espera de AppleEvent. Compartir un solo proceso hace que el límite sea global.

El demonio escucha en un socket de dominio Unix en un directorio 0700 (~/.omnifocus-mcp/daemon-<version>.sock por defecto), por lo que el acceso está controlado por el sistema de archivos: sin puerto de red y sin token. Se cierra solo cuando ningún cliente ha estado conectado durante el período de inactividad, y registra en daemon.log junto al socket.

El nombre del socket incluye la versión del paquete para que una actualización nunca te deje hablando con el demonio de la versión anterior. Justo después de una actualización, es posible que veas brevemente dos demonios: el antiguo sigue sirviendo a los clientes ya conectados a él y se cierra cuando el último de ellos se desconecta. Los clientes que aún están conectados al demonio antiguo reciben un aviso en banda: mientras un demonio más nuevo está sirviendo, cada resultado de herramienta incluye un aviso de actualización de una línea, para que nadie tenga que recordar reconectarse.

Nada cambia en la configuración del cliente. Si el demonio no se puede iniciar (un sandbox inusual, un directorio de inicio de solo lectura), el shim recurre a ejecutar un servidor independiente en el proceso, exactamente como lo hacían las versiones anteriores.

Variables de entorno

Variable	Predeterminado	Propósito
`OMNIFOCUS_MCP_NO_DAEMON`	sin establecer	Establézcalo en `1` para omitir el demonio por completo y ejecutar un servidor dedicado por cliente (el comportamiento anterior al demonio). Lo primero que debe probar si sospecha del demonio.
`OMNIFOCUS_MCP_SOCKET`	`~/.omnifocus-mcp/daemon-<version>.sock`	Anula la ruta del socket, por ejemplo, para ejecutar una instancia aislada.
`OMNIFOCUS_MCP_IDLE_TIMEOUT_MINUTES`	`30`	Salir después de este tiempo sin tráfico de clientes. `0` desactiva el tiempo de espera.
`OMNIFOCUS_MCP_MAX_CONCURRENT_OSASCRIPT`	`4`	Máximo de llamadas `osascript` concurrentes. Redúzcalo si aún ve tiempos de espera de AppleEvent.

Hoja de ruta

Soporte de prompt de MCP
Manipulación de notificaciones para proyectos y tareas
Consulte los problemas de GitHub para solicitudes de funciones y problemas conocidos

Contribuciones

¡Las contribuciones son bienvenidas! No dude en enviar una solicitud de extracción. CI ejecuta verificación de tipos, pruebas unitarias y una compilación en cada PR.

npm install
npm test            # unit tests
npm run build       # compile to dist/
npm run test:integration  # requires OmniFocus; creates and removes TEST:-prefixed items

Licencia

MIT

Available Tools

7 tools

add_omnifocus_taskC

Add a new task to OmniFocus

ParametersJSON Schema

Name	Required	Description
`deferDate`	No	The defer date of the task in ISO format (YYYY-MM-DD or full ISO date)
`dueDate`	No	The due date of the task in ISO format (YYYY-MM-DD or full ISO date)
`estimatedMinutes`	No	Estimated time to complete the task, in minutes
`flagged`	No	Whether the task is flagged or not
`name`	Yes	The name of the task
`note`	No	Additional notes for the task
`projectName`	No	The name of the project to add the task to (will add to inbox if not specified)
`tags`	No	Tags to assign to the task

TDQS

C2.9/5.0

Behavior2/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations provided, the description carries the full burden of behavioral disclosure. While 'Add a new task' implies a write operation, it doesn't specify whether this requires authentication, what happens on success/failure, if there are rate limits, or how errors are handled. For a mutation tool with zero annotation coverage, this is insufficient.

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 a single, efficient sentence that states the core purpose without any wasted words. It's appropriately sized and front-loaded, making it easy for an agent to quickly understand what the tool does.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness2/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a mutation tool with 8 parameters, no annotations, and no output schema, the description is inadequate. It doesn't explain what happens after task creation, what the return value might be, or provide any behavioral context. The description should do more to compensate for the lack of structured metadata.

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 schema fully documents all 8 parameters. The description adds no additional parameter information beyond what's already in the schema. According to scoring rules, when schema coverage is high (>80%), the baseline is 3 even with no param info in the description.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the action ('Add') and resource ('new task to OmniFocus'), making the purpose immediately understandable. It doesn't differentiate from sibling tools like 'add_project' or 'edit_item', which would require mentioning this is specifically for tasks rather than projects or editing existing items.

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?

No guidance is provided on when to use this tool versus alternatives like 'add_project', 'edit_item', or 'batch_add_items'. The description doesn't mention prerequisites, context, or any exclusions that would help an agent choose between these sibling tools.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

add_projectC

Add a new project to OmniFocus

ParametersJSON Schema

Name	Required	Description
`deferDate`	No	The defer date of the project in ISO format (YYYY-MM-DD or full ISO date)
`dueDate`	No	The due date of the project in ISO format (YYYY-MM-DD or full ISO date)
`estimatedMinutes`	No	Estimated time to complete the project, in minutes
`flagged`	No	Whether the project is flagged or not
`folderName`	No	The name of the folder to add the project to (will add to root if not specified)
`name`	Yes	The name of the project
`note`	No	Additional notes for the project
`sequential`	No	Whether tasks in the project should be sequential (default: false)
`tags`	No	Tags to assign to the project

TDQS

C2.9/5.0

Behavior2/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations are provided, so the description carries the full burden of behavioral disclosure. It states the tool adds a project but doesn't explain what happens upon success (e.g., returns a project ID), error conditions, permissions needed, or side effects. This is inadequate for a mutation tool with zero annotation coverage.

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 a single, efficient sentence that directly states the tool's purpose without any wasted words. It's appropriately sized and front-loaded, making it easy for an AI agent to parse quickly.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness2/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a mutation tool ('add') with no annotations and no output schema, the description is insufficient. It doesn't cover behavioral aspects like return values, error handling, or system impacts, leaving significant gaps for an AI agent to understand how to use it effectively.

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 schema already documents all 9 parameters thoroughly. The description adds no additional parameter information beyond what's in the schema. According to the rules, with high schema coverage, the baseline is 3 even with no param info in the description.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the action ('Add a new project') and target resource ('to OmniFocus'), which is specific and unambiguous. However, it doesn't differentiate from sibling tools like 'add_omnifocus_task' or 'batch_add_items' that might also create items in OmniFocus, so it doesn't reach the highest score.

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 provides no guidance on when to use this tool versus alternatives. It doesn't mention when to choose 'add_project' over 'add_omnifocus_task' (for tasks vs. projects) or 'batch_add_items' (for bulk operations), nor does it specify prerequisites or exclusions for project creation.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

batch_add_itemsB

Add multiple tasks or projects to OmniFocus in a single operation

ParametersJSON Schema

Name	Required	Description	Default
`items`	Yes	Array of items (tasks or projects) to add

TDQS

B3.2/5.0

Behavior2/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations provided, the description carries full burden but only states it's a batch addition operation. It doesn't disclose behavioral traits such as whether it's idempotent, requires specific permissions, handles errors, or returns any output. For a mutation tool with zero annotation coverage, this is a significant gap in transparency.

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 a single, efficient sentence that front-loads key information ('Add multiple tasks or projects') without unnecessary words. It earns its place by clarifying the batch nature and target system, making it appropriately sized and well-structured.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness2/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given no annotations and no output schema, the description is incomplete for a mutation tool. It lacks details on behavioral context, error handling, or return values, which are crucial for an agent to use it correctly. The high schema coverage doesn't compensate for these gaps in operational transparency.

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?

The schema description coverage is 100%, so the schema fully documents the 'items' parameter and its nested properties. The description adds no parameter semantics beyond implying batch processing, which is already covered by the tool name and schema. Baseline 3 is appropriate as the schema does the heavy lifting.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the action ('Add multiple tasks or projects') and target ('to OmniFocus in a single operation'), making the purpose evident. It distinguishes from single-item tools like 'add_omnifocus_task' and 'add_project' by emphasizing batch capability, though it doesn't explicitly name these siblings.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines3/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description implies usage for adding multiple items at once, suggesting it's an alternative to single-item tools. However, it doesn't explicitly state when to use this over siblings like 'add_omnifocus_task' or 'add_project', nor does it mention prerequisites or exclusions, leaving guidance incomplete.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

batch_remove_itemsC

Remove multiple tasks or projects from OmniFocus in a single operation

ParametersJSON Schema

Name	Required	Description	Default
`items`	Yes	Array of items (tasks or projects) to remove

TDQS

C2.9/5.0

Behavior2/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations are provided, so the description carries full burden. It states 'Remove' which implies a destructive mutation, but lacks details on permissions, reversibility, confirmation prompts, or error handling for partial failures. For a batch deletion tool with no annotation coverage, this is a significant gap in behavioral disclosure.

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 a single, efficient sentence that front-loads the core action and resource. Every word earns its place with no redundancy or fluff, making it highly concise and well-structured for quick comprehension.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness2/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the tool's complexity (batch destructive operation) and lack of annotations and output schema, the description is insufficient. It doesn't cover critical aspects like return values, error conditions, or side effects. For a mutation tool with no structured safety hints, more completeness is needed to guide safe agent usage.

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 schema fully documents the 'items' parameter and its nested properties (id, itemType, name). The description adds no additional parameter semantics beyond implying batch processing. With high schema coverage, the baseline is 3, as the description doesn't compensate but doesn't need to heavily.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the action ('Remove multiple tasks or projects') and resource ('from OmniFocus') with the scope of 'in a single operation'. It distinguishes from the sibling 'remove_item' by emphasizing batch capability, though it doesn't explicitly name that sibling. The purpose is specific but could be more precise about differentiation.

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 provides no guidance on when to use this tool versus alternatives like 'remove_item' or other deletion methods. It mentions batch removal but doesn't specify scenarios (e.g., efficiency for bulk cleanup) or prerequisites. Without explicit when/when-not instructions, usage context is implied at best.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

dump_databaseC

Gets the current state of your OmniFocus database

ParametersJSON Schema

Name	Required	Description	Default
`hideCompleted`	No	Set to false to show completed and dropped tasks (default: true)
`hideRecurringDuplicates`	No	Set to true to hide duplicate instances of recurring tasks (default: true)

TDQS

C2.9/5.0

Behavior2/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations provided, the description carries full burden for behavioral disclosure. While 'Gets' implies a read operation, it doesn't specify what 'current state' includes (tasks, projects, tags, etc.), the format of the output, whether this is a heavy operation, or any performance considerations. For a database dump tool with zero annotation coverage, this is insufficient.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single, efficient sentence that states the core purpose upfront. However, given the complexity of a database dump operation and the many sibling alternatives, this extreme conciseness comes at the cost of helpful context that would aid tool selection.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness2/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a database dump tool with no annotations, no output schema, and 15 sibling retrieval tools, the description is incomplete. It doesn't explain what data is included in the dump, the output format, how this differs from more targeted retrieval tools, or any performance implications. The agent lacks sufficient context to use this tool effectively.

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 schema already fully documents both parameters (hideCompleted and hideRecurringDuplicates). The description adds no parameter information beyond what's in the schema, meeting the baseline 3 for high schema coverage.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the action ('Gets') and resource ('current state of your OmniFocus database'), providing a specific verb+resource combination. However, it doesn't explicitly distinguish this tool from its many sibling tools that also retrieve task/project data (like get_flagged_tasks, get_inbox_tasks, etc.), which would require a 5.

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 provides no guidance on when to use this tool versus alternatives. With 15 sibling tools that retrieve various subsets of OmniFocus data, the agent receives no help in choosing between a full database dump and more targeted retrieval tools like get_flagged_tasks or filter_tasks.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

edit_itemC

Edit a task or project in OmniFocus

ParametersJSON Schema

Name	Required	Description
`addTags`	No	Tags to add to the task
`id`	No	The ID of the task or project to edit
`itemType`	Yes	Type of item to edit ('task' or 'project')
`name`	No	The name of the task or project to edit (as fallback if ID not provided)
`newDeferDate`	No	New defer date in ISO format (YYYY-MM-DD or full ISO date); set to empty string to clear
`newDueDate`	No	New due date in ISO format (YYYY-MM-DD or full ISO date); set to empty string to clear
`newEstimatedMinutes`	No	New estimated minutes
`newFlagged`	No	Set flagged status (set to false for no flag, true for flag)
`newFolderName`	No	New folder to move the project to
`newName`	No	New name for the item
`newNote`	No	New note for the item
`newProjectStatus`	No	New status for projects
`newSequential`	No	Whether the project should be sequential
`newStatus`	No	New status for tasks (incomplete, completed, dropped)
`removeTags`	No	Tags to remove from the task
`replaceTags`	No	Tags to replace all existing tags with

TDQS

C2.9/5.0

Behavior2/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations provided, the description carries full burden for behavioral disclosure but only states the basic purpose. It doesn't mention that this is a mutation operation (implied by 'Edit'), what permissions are needed, whether changes are reversible, error conditions, or what happens when multiple parameters are provided simultaneously (e.g., addTags vs replaceTags).

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 a single, efficient sentence that states the core purpose without unnecessary words. It's appropriately sized for a tool with comprehensive schema documentation, though it could benefit from additional context about usage and behavior.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness2/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a complex mutation tool with 16 parameters, no annotations, and no output schema, the description is inadequate. It doesn't explain what the tool returns, error handling, or behavioral nuances. The agent must rely entirely on the input schema for understanding, which lacks context about how the edit operation actually works in practice.

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 all parameters are documented in the schema itself. The description adds no additional parameter information beyond what's in the schema. According to scoring rules, when schema coverage is high (>80%), the baseline is 3 even with no param info in description.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the action ('Edit') and target ('a task or project in OmniFocus'), providing specific verb+resource. However, it doesn't distinguish this from sibling tools like 'remove_item' or 'add_omnifocus_task' beyond the basic edit vs add/remove distinction, missing opportunities to clarify scope boundaries.

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 provides no guidance on when to use this tool versus alternatives. It doesn't mention prerequisites (like needing an existing item ID), when to choose edit over remove+add, or how it differs from batch operations available in sibling tools like 'batch_add_items' or 'batch_remove_items'.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

remove_itemC

Remove a task or project from OmniFocus

ParametersJSON Schema

Name	Required	Description
`id`	No	The ID of the task or project to remove
`itemType`	Yes	Type of item to remove ('task' or 'project')
`name`	No	The name of the task or project to remove (as fallback if ID not provided)

TDQS

C2.9/5.0

Behavior2/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations provided, the description carries full burden but only states the action without behavioral details. It doesn't disclose if removal is permanent, requires specific permissions, has side effects, or what happens to dependent items, which is critical for a destructive operation.

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 a single, efficient sentence that front-loads the core action and resource without any wasted words. It's appropriately sized for a simple tool, making it easy to parse quickly.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness2/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a destructive tool with no annotations and no output schema, the description is incomplete. It lacks critical context such as the permanence of removal, error handling, or return values, leaving significant gaps for safe agent 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 schema fully documents all parameters. The description adds no extra meaning beyond implying removal targets tasks or projects, matching the schema. Baseline 3 is appropriate as the schema handles parameter semantics adequately.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the action ('Remove') and the resource ('a task or project from OmniFocus'), making the purpose immediately understandable. It doesn't distinguish from sibling tools like 'batch_remove_items' or 'edit_item', which prevents a perfect score.

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 provides no guidance on when to use this tool versus alternatives like 'batch_remove_items' for multiple items or 'edit_item' for modifications. It also doesn't mention prerequisites or context for removal, leaving usage unclear.

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.

7 tool updatesv1.0.0Aug 14, 2025
- First observedadd_omnifocus_task
- First observedadd_project
- First observedbatch_add_items
- First observedbatch_remove_items
- First observeddump_database
- First observededit_item
- First observedremove_item

Deploy Server

Pay for results, not tokens.Fund a bounty. Let AI agents compete and collaborate to solve your problems.agentbounties.appAd

TDQS

A3.5/5.0

Scored 2026-04-18 10:25 across 7 tools

Disambiguation4/5

Most tools have distinct purposes, but there is some overlap between 'remove_item' and 'batch_remove_items', and 'edit_item' could be confused with individual add/edit operations. The descriptions help clarify, but the boundaries between single and batch operations are not perfectly clear.

Naming Consistency5/5

All tool names follow a consistent snake_case pattern with clear verb_noun structure (e.g., add_omnifocus_task, edit_item, dump_database). There are no deviations in naming conventions, making the set predictable and readable.

Tool Count5/5

With 7 tools, the count is well-scoped for managing tasks and projects in OmniFocus. Each tool serves a clear purpose, from basic CRUD operations to batch processing and database inspection, without feeling excessive or insufficient.

Completeness5/5

The tool set provides complete coverage for the OmniFocus domain, including create (add_task, add_project), read (dump_database), update (edit_item), and delete (remove_item, batch_remove_items) operations, plus batch additions. There are no obvious gaps that would hinder agent workflows.

Maintenance

ActivityActive

ResponsivenessWithin a week

Resources

Need Help?

Related Servers

Related MCP Connectors

hithereiamaliff-mcp-nextcloudOAuth
ai.smithery
A comprehensive Model Context Protocol (MCP) server that enables AI assistants to interact with yo…
Cloud Storage File Systems Workplace & Productivity
238
mcpOAuth
net.todoist
Official Todoist MCP server for AI assistants to manage tasks, projects, and workflows.
App Automation Workplace & Productivity Project Management
2
mcp-serverOAuth
com.niftypm
Nifty's MCP server — exposes tasks, projects, messages, and files as tools for AI agents.
Project Management Communication File Systems
2
ContexterOAuth
io.github.maaakso
Share one project context across ChatGPT, Claude, Telegram and any MCP client.
Knowledge & Memory Note Taking
1

Related MCP Servers

OmniFocus MCP Server
App Automation Developer Tools Project Management
mdoel
A
license
A
quality
D
maintenance
A Model Context Protocol server that integrates OmniFocus with Claude Desktop, providing AI-powered access to tasks and projects for enhanced task management and weekly reviews.
Updated a year ago (2025-06-20 01:58 UTC)
4
323 npm
8
MIT
MCP OmniFocus
App Automation Project Management
someposer
A
license
B
quality
D
maintenance
A Model Context Protocol server that enables automation and management of OmniFocus tasks, projects, and tags using natural language and programmable interfaces from VS Code, command line, or any MCP-compatible client.
Updated a year ago (2025-06-22 22:18 UTC)
12
MIT
OmniFocus MCP
Project Management Workplace & Productivity
vitalyrodnenko
A
license
Not graded
quality
D
maintenance
MCP server that gives AI assistants full control over OmniFocus on macOS, including tasks, projects, tags, folders, perspectives, forecast, notifications, and review workflows.
Updated 6 months ago (2026-04-06 04:39 UTC)
43
MIT
OmniFocus MCP Server
Project Management Search
estrenuo
A
license
A
quality
B
maintenance
An MCP server that enables AI assistants to interact with OmniFocus on macOS via JXA, supporting task, project, folder, tag, perspective, and search operations.
Updated 2 months ago (2026-08-15 07:45 UTC)
31
20 npm
MIT

Servidor MCP de OmniFocus

Resumen

Inicio rápido

Requisitos previos

Claude Desktop

Claude Code

Ejemplos de conversación

Herramientas

query_omnifocus

dump_database

add_omnifocus_task

add_project

edit_item

remove_item

batch_add_items

batch_remove_items

list_perspectives

get_perspective_view

list_tags

create_tag

Elementos recurrentes

Recursos

Instrucciones del servidor y registro

Cómo funciona

Demonio compartido

Variables de entorno

Hoja de ruta

Contribuciones

Licencia

Available Tools

Tool Schema Changelog

Maintenance

Resources

Related MCP Connectors

Related MCP Servers

Appeared in Searches

`query_omnifocus`

`dump_database`

`add_omnifocus_task`

`add_project`

`edit_item`

`remove_item`

`batch_add_items`

`batch_remove_items`

`list_perspectives`

`get_perspective_view`

`list_tags`

`create_tag`