MCP server de Layerdock
Commit 19 oct 2026Permite que los agentes de programación lean comentarios de sitios web, vean capturas de pantalla y accedan a trazas de la consola para corregir errores directamente desde el editor.
También conocido como LayerDock/layerdock-mcp
- Stars
- 0
- Herramientas
- 5
- Descargas, 30 días
- —
- Última versión
- —
- Último commit
- 19 oct 2026
- Licencia
- MIT
¿Qué es Layerdock MCP?
Permite que los agentes de programación lean comentarios de sitios web, vean capturas de pantalla y accedan a trazas de la consola para corregir errores directamente desde el editor. Expone 5 herramientas, como list_docks, list_feedback, get_feedback.
Resumen generado a partir del README del proyecto
Acerca del MCP server de Layerdock
Corregir errores de sitios web directamente desde tu editor de código es lo que layerdock-mcp permite a los desarrolladores que utilizan agentes de IA. Al conectarse con LayerDock, los agentes de programación pueden acceder a los comentarios del sitio web, ver capturas de pantalla capturadas y examinar trazas de consola o de red para comprender los problemas reportados. Esta integración funciona con clientes como Claude Code, Cursor, Codex CLI y Windsurf mediante una configuración local usando un token de acceso personal.
El servidor proporciona herramientas específicas para gestionar el flujo de trabajo de depuración. Los desarrolladores pueden usar list_docks para ver sus sitios, list_feedback para encontrar problemas abiertos y get_feedback para recibir un resumen detallado para la corrección. Este resumen incluye selectores CSS, estilos computados e incluso una cadena de búsqueda diseñada para coincidir con el código fuente con precisión. La herramienta get_feedback también admite diferentes niveles de detalle, como auto, minimal o full, para gestionar la cantidad de datos devueltos.
Más allá de solo leer datos, el servidor permite que los agentes interactúen con el ciclo de retroalimentación. Puedes usar update_feedback_status para mover un pin a través de tu flujo de trabajo o reply_to_feedback para publicar comentarios en un hilo. Cualquier respuesta enviada por un agente se etiqueta automáticamente para distinguirla de las respuestas humanas, garantizando una comunicación clara dentro de tu equipo.
Qué puedes hacer con él
- 1Identificar errores de sitios web pendientesPide a tu agente de IA que encuentre todos los elementos de feedback abiertos en todos tus sitios conectados para priorizar tu trabajo.
- 2Depurar problemas de diseño o comportamientoProporciona al agente un resumen detallado que contenga capturas de pantalla y errores de consola para diagnosticar un error de UI específico.
- 3Comunicar correcciones a tus compañerosHaz que el agente publique una respuesta en un hilo de feedback una vez que se haya solucionado un error.
Escrito a partir del README del proyecto. Cada caso de uso se verifica con una cita del mismo.
Herramientas de Layerdock MCP 5
Detectado desde el READMElist_dockslist_feedbackget_feedbackupdate_feedback_statusreply_to_feedback
| list_docks | — | |
| list_feedback | — | |
| get_feedback | — | |
| update_feedback_status | — | |
| reply_to_feedback | — |
Configuración
LAYERDOCK_TOKEN
| Nombre | Descripción | Tipo |
|---|---|---|
| LAYERDOCK_TOKEN | — |
Verificaciones automáticas
Ejecutado 14 nov 2026Informe completo →Aún no verificado. Un servidor necesita una puntuación de 80, ningún hallazgo grave y suficientes datos para que podamos revisarlo. Cómo funcionan las verificaciones · Qué corregir para obtener más puntos
- Repositorio de origen vinculado y accesiblelayerdock/layerdock-mcp is public and reachablegithub.com/layerdock/layerdock-mcp ↗Aprobado
- El paquete indica este repositorio como su origenNo verificado
- Procedencia de la compilación (atestación de Sigstore)No verificado
- Licencia de código abierto (OSI)MITspdx.org/licenses/MIT.html ↗Aprobado
- Commit o lanzamiento en el último añoLast commit or release 2026-10-19github.com/layerdock/layerdock-mcp ↗Aprobado
- OpenSSF ScorecardNo verificado
- El nombre del paquete no es similar a un paquete popularNo verificado
- No hay avisos críticos en el paquete ni en sus dependenciasNo verificado
- Sin instrucciones ocultas para el modelo5 tool descriptions and the README read; no override phrases, credential paths or hidden charactersAprobado
- Las herramientas destructivas están etiquetadasNo tool named like delete, drop or execAprobado
- El endpoint remoto responde al handshake de MCPNo verificado
README
Ver en GitHub@layerdock/mcp
Read your LayerDock website feedback — with the CSS selector, the screenshot, and the console/network trace captured at report time — directly in your coding agent. Fix the bug, reply on the thread, mark it resolved, without leaving the editor.
Setup
-
Create a token at https://www.layerdock.io/dashboard/integrations/mcp
-
Warm the cache first, once, in a terminal:
npx -y @layerdock/mcp --versionnpxdownloads the package on first use, and a cold download can take longer than an editor's MCP connect timeout (30s in Claude Code) — so the very first connection fails withCONNECT_TIMEOUTon a server that is working perfectly. Running it once puts it in the npx cache; every launch after that is instant. Skip this and you may simply need to restart your editor once. -
Add the config for your client below.
The three clients below are the short version. The full walkthrough — config for Claude Code, Cursor, Codex CLI, Antigravity, Windsurf, VS Code and Zed, how to verify the connection, and what to check when the server does not appear — is at https://www.layerdock.io/docs/connect-your-coding-agent
Claude Code
.mcp.json in your project root:
{
"mcpServers": {
"layerdock": {
"command": "npx",
"args": ["-y", "@layerdock/mcp"],
"env": { "LAYERDOCK_TOKEN": "ldk_..." }
}
}
}
Cursor
~/.cursor/mcp.json — same JSON as above.
Codex CLI
~/.codex/config.toml:
[mcp_servers.layerdock]
command = "npx"
args = ["-y", "@layerdock/mcp"]
env = { LAYERDOCK_TOKEN = "ldk_..." }
Tools
| Tool | What it does |
|---|---|
list_docks |
Your sites, with any codebase hints their owner declared (framework, source root, CMS) |
list_feedback |
Pins, filterable by status. dockId is optional — omit it to see open work across every dock you can reach, which is the whole answer to "what needs my attention?" in one call |
get_feedback |
One pin as a fix brief, plus the screenshot as an image. Takes detail: auto (default), minimal, full |
update_feedback_status |
Move a pin through the workflow |
reply_to_feedback |
Post a reply on the thread, attributed to you and labelled as coming via a coding agent |
What get_feedback actually returns
A fix brief, ordered by how actionable each part is:
- What the reporter wants changed, plus the reply thread
- The component, when the reviewed site is a dev/unminified build — sometimes the source file and line
- A repetition warning when the pinned element is one of N identical siblings, so an agent doesn't hardcode a one-item fix into the shared component that renders all of them
- A search string that actually matches source — one contiguous run of
literal text from a single text node, whitespace collapsed, never cut
mid-word. This is deliberately not the element's
innerText: that spans child nodes, so it carries newlines and fragments that appear in no source file and a literal grep for it never matches - Where it is — page URL, section, CSS selector, and the full visible text marked explicitly as context rather than as something to grep for
- Structure and computed styles at pin time
- Console errors and failed/slow requests from the moment of capture, each stamped with how long before the report it happened
- The screenshot, as an image block the agent can actually look at — downscaled server-side, and when a pin has no capture the brief says so instead of instructing the agent to consult an image that was never attached
It also states what it cannot tell you — the brief never claims to know your
repository layout, and it instructs the agent to locate and confirm the file
before editing rather than guessing. That includes the case where the fix is not
in the repository at all: if the visible text appears nowhere in the codebase,
the content is probably CMS- or API-driven and the fix belongs in the content
source. Set a dock's cms field and the brief names the system directly.
Payload size
get_feedback defaults to detail: "auto". A pin that reads as a pure copy
change ("fix this wording") does not need ~20 computed CSS properties, device
memory, hardware concurrency and network downlink — so those are dropped, and
the brief says it dropped them. A layout or behaviour bug keeps everything. Pass
detail: "full" to override, or "minimal" to always trim.
Permissions
The token acts as you, and says so. A reply posted through reply_to_feedback
is attributed to the person the token belongs to and labelled as arriving via
a coding agent — the reviewer reading the thread is deciding whether to re-check
the page themselves, and a person promising "fixed this" is not the same claim as
an agent asserting it. Both facts are stamped server-side from the authenticated
token, so neither can be chosen by the client. Do not sign the message text
yourself.
Anything you cannot do in the dashboard, the agent cannot
do either — role gating is enforced server-side, not here. A member who is not
assigned to a pin cannot change its status, and nobody can read a dock they have
no relationship to.
Configuration
| Env var | Purpose |
|---|---|
LAYERDOCK_TOKEN |
Required. Your personal access token (ldk_...). |
LAYERDOCK_API_URL |
Optional. Defaults to https://www.layerdock.io. Point it at a local dev server when working on LayerDock itself. |
Security
Tokens are stored as a SHA-256 hash — the plaintext is shown once, at creation, and is never recoverable afterwards. Revoke a token from the same settings page; revocation takes effect immediately.
An authentication failure names its actual cause — malformed, unknown, deleted,
or expired — and echoes the first 12 characters of the token the server received
(received "ldk_AbCd-EfG…"). That prefix is the same non-secret value the
dashboard already displays next to each token, and it is what tells a stale
client process still holding a replaced token apart from a genuinely bad one.
Note that on a dev build, sourceFile in a brief may be an absolute path from
the machine that built the reviewed site. That stays within the dock's own
trust boundary, but it is worth knowing before sharing a brief outside your team.
License
MIT
Preguntas sobre Layerdock MCP
¿Qué herramientas proporciona Layerdock MCP?
Expone 5 herramientas, incluidas list_docks, list_feedback, get_feedback, update_feedback_status, reply_to_feedback.
¿Qué información incluye un resumen de comentarios?
El resumen incluye la solicitud del informante, el componente o archivo fuente, una cadena de búsqueda coincidente, la URL de la página, selectores CSS, estilos computados, errores de consola y una captura de pantalla.
¿Puede el agente realizar acciones para las que no estoy autorizado en el dashboard?
No, el agente está sujeto a las mismas restricciones de roles que tu cuenta del dashboard; si tú no puedes realizar una acción, el agente tampoco podrá.