En las novelas visuales y Galgames, una "bandera" (フラグ) es el momento en que una elección desencadena una nueva rama de la historia. Una decisión lo cambia todo.
Flag MCP lleva ese mismo poder a la programación asistida por IA. Cuando tu asistente de IA llega a una encrucijada, no adivina: levanta una bandera y espera a que elijas la ruta.
🎮 Tú eres el protagonista. La IA espera en cada punto de ramificación.
💎 Cada bandera define la ruta. Se acabaron las reescrituras especulativas.
🚀 Interacción rica. Texto, capturas de pantalla, anotaciones: todo tu arsenal.
Esto transforma la programación con IA de "esperar que funcione" a una narrativa donde tú tienes el control.
Ámbito de aplicación:
Planes de programación facturados por solicitud.
Desarrolladores que desean controlar el comportamiento de la IA.
Related MCP server: Human-In-the-Loop MCP Server
❌ Sin Flag MCP | ✅ Con Flag MCP |
La IA adivina → código incorrecto → reescritura dolorosa | La IA levanta una bandera → tú eliges → código correcto |
Múltiples rondas de "espera, ¿qué quisiste decir?" | Un diálogo estructurado, claro como el cristal |
Ansiedad: "¡¿Qué va a hacer la IA ahora?!" | Confianza: cada acción confirmada por ti |
Pasajero indefenso | Tú eres quien marca la ruta |
🖥️ Interfaz de usuario en modo oscuro — Un elegante diálogo de escritorio nativo que se adapta a tu flujo de trabajo
✅ Opciones de ruta — Opciones predefinidas estructuradas (estilo casilla de verificación)
💬 Texto libre — Cuando las rutas predefinidas no son suficientes, escribe tu propio guion
📷 Arsenal multimedia enriquecido
Pegar imágenes desde el portapapeles
Seleccionar archivos locales
Captura de pantalla + Anotador integrado (rectángulo, círculo, flecha, lápiz, texto, recorte)
🖼️ Imágenes de aviso — La IA puede mostrarte imágenes (rutas locales, file://, http(s)://)
🔒 Seguridad primero — Imágenes remotas validadas, con límite de tamaño y carga asíncrona
🎨 Optimizado para macOS — Manejo adecuado de iconos y pulido visual
Python >= 3.11
uv (recomendado) o pip
git clone https://github.com/pauoliva/interactive-feedback-mcp.git
cd interactive-feedback-mcp
uv syncAñádelo a la configuración de tu cliente MCP:
Cursor (mcp.json) / Claude Desktop (claude_desktop_config.json):
{
"mcpServers": {
"interactive-feedback": {
"command": "uv",
"args": [
"--directory",
"/path/to/interactive-feedback-mcp",
"run",
"server.py"
],
"timeout": 900000,
"autoApprove": ["interactive_feedback"]
}
}
}⚠️ Nota: El tiempo de espera está en milisegundos para Cursor (
900000= 15 min). Algunos clientes usan segundos; ajústalo en consecuencia.
interactive_feedbackParámetro | Tipo | Descripción |
|
| La pregunta/aviso a mostrar |
|
| Opcional. Opciones de ruta para decisiones rápidas |
|
| Opcional. Imágenes a mostrar (URLs locales/remotas) |
Comentarios de texto del usuario
Archivos adjuntos de imagen opcionales (como bloques de contenido de imagen MCP)
Añade esto a las instrucciones personalizadas de tu asistente de IA:
If requirements are unclear, call interactive_feedback before implementing.
Present predefined options whenever possible — give the user clear route choices.
Before finishing a task, call interactive_feedback once more for final confirmation.Variable | Predeterminado | Descripción |
|
| Tiempo de vida máximo del proceso de la UI |
| — | Ruta del icono de la aplicación personalizada |
|
| Tiempo de espera de obtención de imagen remota |
|
| Tamaño máximo de imagen remota (10MB) |
✅ Imágenes remotas validadas por tipo de contenido (image/*)
✅ Cargas útiles grandes rechazadas mediante límite de tamaño
✅ La obtención asíncrona mantiene la UI receptiva
✅ Archivos locales leídos solo cuando se hace referencia explícita a ellos
Licencia MIT: haz un fork, ponle una bandera, despliégalo.
🚩 Planta tu bandera. Escribe tu propia ruta.
Hecho con 💜 para desarrolladores que se niegan a ser NPCs en su propia base de código.
Request interactive feedback from the user. Supports text and image attachments. 使用方式:
当你通过此工具询问用户时,务必说明需要用户确定的内容。
请在完成用户布置的工作后调用该工具时,提供"结束"的选项,如果用户选择,则本次请求结束. 使用技巧:
请给出可选项,让用户选择,选项中请包涵你最推荐的选项,并说明理由.
针对每个选项,请给出对应的描述,让用户了解每个选项的含义. 什么时候使用:
每当你全部工作完成时，请调用此工具，而非直接结束流程.
每当你遇到需要用户确定的点时(例如进行需求讨论,或者执行任务中遇到重要分岔路口时),务必调用此工具.
| Name | Required | Description | Default |
|---|---|---|---|
| message | No | The specific question for the user | |
| predefined_options | No | Predefined options for the user to choose from (optional) | |
| message_images | No | Image paths to render in the prompt area (optional) |
| Name | Required | Description |
|---|---|---|
| result | Yes |
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. It explains the interaction pattern (blocking request for user input, option-based responses) but lacks technical behavioral traits such as timeout behavior, session persistence, or data handling. It covers 'how to use' but omits 'what happens under the hood' details expected for a user-input 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?
The description uses clear structural headers (Usage method, Usage tips, When to use) but is verbose due to extensive bilingual content. The Chinese examples, while helpful for behavior modeling, make the description longer than necessary for agent consumption, and the language mixing reduces structural coherence.
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?
Given the presence of an output schema, the description appropriately focuses on behavioral guidance rather than return values. It comprehensively covers invocation patterns and option structuring, though it would benefit from mentioning timeout handling or error conditions for full completeness.
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%, establishing a baseline of 3. The description adds semantic value beyond the schema by specifying in the Chinese text that predefined_options should include a recommended choice with rationale and an 'end' option, providing substantive usage guidance for parameter population that the raw schema lacks.
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 opening sentence clearly states the tool requests interactive feedback and supports text/image attachments. However, the extensive Chinese instructions, while useful, create a bilingual structure that slightly reduces immediate clarity for agents parsing primarily English content.
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 Chinese text under '什么时候使用' (when to use) provides explicit when/when-not guidance, specifically stating to invoke this tool when work is completed instead of directly ending the process, and when encountering decision points requiring user confirmation. It also explicitly references '使用方式' (usage method) and '使用技巧' (usage tips) for detailed alternatives.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
v0.1.1interactive_feedbackScored across 1 tool
With only one tool available, there is no ambiguity or risk of tool misselection. The single tool has a clear, distinct purpose that does not overlap with any other tools.
The single tool follows a clear snake_case naming convention. While 'interactive' is an adjective rather than a verb, there are no other tools to create inconsistency, so the naming pattern is uniform.
A single tool is insufficient for the apparent 'Flag' domain suggested by the server name. Even for a minimal utility server, one generic feedback tool represents a severely undersized tool surface that likely cannot fulfill the server's intended purpose.
The server named 'Flag MCP' implies a feature flag or flagging domain, yet provides only a generic user feedback tool with no flag creation, management, querying, or lifecycle operations. This represents a severely incomplete surface for the stated purpose.
Human-in-the-loop for AI coding agents — ask questions, get approvals via Slack.
Give any AI agent a way to ask a person — for approval, a decision, an answer or a review.
Build and edit app screen mockups and clickable prototypes from your AI assistant.
Adaptive plan/build/review cycles for AI coding assistants, persisted across sessions.
