Layerdock MCP server
Commit 19. Okt. 2026Ermöglicht es Coding Agents, Website-Feedback zu lesen, Screenshots einzusehen und Console-Traces abzurufen, um Bugs direkt aus dem Editor heraus zu beheben.
Auch bekannt als LayerDock/layerdock-mcp
- Stars
- 0
- Tools
- 5
- Downloads, 30 Tage
- —
- Neueste Version
- —
- Letzter Commit
- 19. Okt. 2026
- Lizenz
- MIT
Was ist Layerdock MCP?
Ermöglicht es Coding Agents, Website-Feedback zu lesen, Screenshots einzusehen und Console-Traces abzurufen, um Bugs direkt aus dem Editor heraus zu beheben. Er stellt 5 Tools bereit, etwa list_docks, list_feedback, get_feedback.
Zusammenfassung generiert aus dem README des Projekts
Über Layerdock MCP server
Das Beheben von Website-Bugs direkt aus deinem Code-Editor heraus ist das, was layerdock-mcp für Entwickler ermöglicht, die AI Agents nutzen. Durch die Verbindung zu LayerDock können Coding Agents auf Website-Feedback zugreifen, erfasste Screenshots ansehen und Console- oder Network-Traces untersuchen, um gemeldete Probleme zu verstehen. Diese Integration funktioniert mit Clients wie Claude Code, Cursor, Codex CLI und Windsurf über eine lokale Konfiguration mittels eines Personal Access Tokens.
Der Server stellt spezifische Tools bereit, um den Debugging-Workflow zu verwalten. Entwickler können list_docks nutzen, um ihre Sites anzuzeigen, list_feedback, um offene Issues zu finden, und get_feedback, um einen detaillierten Fix-Brief zu erhalten. Dieser Brief enthält CSS-Selektoren, berechnete Styles und sogar einen Search-String, der darauf ausgelegt ist, den Quellcode präzise zu matchen. Das get_feedback Tool unterstützt zudem verschiedene Detailstufen wie auto, minimal oder full, um die Menge der zurückgegebenen Daten zu steuern.
Über das reine Lesen von Daten hinaus ermöglicht der Server den Agents, mit dem Feedback-Loop zu interagieren. Du kannst update_feedback_status nutzen, um einen Pin durch deinen Workflow zu bewegen, oder reply_to_feedback, um Kommentare in einem Thread zu posten. Alle Antworten, die von einem Agent gesendet werden, werden automatisch markiert, um sie von menschlichen Antworten zu unterscheiden, was eine klare Kommunikation in deinem Team sicherstellt.
Was du damit machen kannst
- 1Ausstehende Website-Bugs identifizierenBitte deinen AI Agent, alle offenen Feedback-Items über alle deine verbundenen Sites hinweg zu finden, um deine Arbeit zu priorisieren.
- 2Layout- oder Verhaltensprobleme debuggenVersorge den Agent mit einem detaillierten Brief, der Screenshots und Console-Errors enthält, um einen spezifischen UI-Bug zu diagnostizieren.
- 3Fixes an Teammitglieder kommunizierenLass den Agent eine Antwort in einem Feedback-Thread posten, sobald ein Bug behoben wurde.
Geschrieben aus dem README des Projekts. Jeder Use Case wurde gegen ein Zitat daraus geprüft.
Layerdock MCP tools 5
Erkannt aus dem READMElist_dockslist_feedbackget_feedbackupdate_feedback_statusreply_to_feedback
| list_docks | — | |
| list_feedback | — | |
| get_feedback | — | |
| update_feedback_status | — | |
| reply_to_feedback | — |
Konfiguration
LAYERDOCK_TOKEN
| Name | Beschreibung | Typ |
|---|---|---|
| LAYERDOCK_TOKEN | — |
Automatisierte Checks
Geluften am 14. Nov. 2026Vollständiger Bericht →Noch nicht verifiziert. Ein Server benötigt einen Score von 80, keine kritischen Befunde und genug Daten für unsere Prüfung. Wie die Checks funktionieren · Was du für mehr Punkte verbessern kannst
- Source Repository verknüpft und erreichbarlayerdock/layerdock-mcp is public and reachablegithub.com/layerdock/layerdock-mcp ↗Bestanden
- Paket nennt dieses Repository als QuelleNicht geprüft
- Build-Provenienz (Sigstore-Attestierung)Nicht geprüft
- Open Source Lizenz (OSI)MITspdx.org/licenses/MIT.html ↗Bestanden
- Commit oder Release im letzten JahrLast commit or release 2026-10-19github.com/layerdock/layerdock-mcp ↗Bestanden
- OpenSSF ScorecardNicht geprüft
- Package-Name ähnelt keinem populären PackageNicht geprüft
- Keine kritischen Advisories im Paket oder seinen AbhängigkeitenNicht geprüft
- Keine versteckten Anweisungen an das Modell5 tool descriptions and the README read; no override phrases, credential paths or hidden charactersBestanden
- Destruktive Tools sind markiertNo tool named like delete, drop or execBestanden
- Remote-Endpoint beantwortet den MCP-HandshakeNicht geprüft
README
Auf GitHub ansehen@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
Layerdock MCP Fragen
Welche Tools bietet Layerdock MCP?
Er stellt 5 Tools bereit, darunter list_docks, list_feedback, get_feedback, update_feedback_status, reply_to_feedback.
Welche Informationen sind in einem Feedback-Brief enthalten?
Der Brief enthält die Anfrage des Meldenden, die Komponente oder die Quelldatei, einen passenden Search-String, die Seiten-URL, CSS-Selektoren, berechnete Styles, Console-Errors und einen Screenshot.
Kann der Agent Aktionen ausführen, für die ich im Dashboard nicht autorisiert bin?
Nein, der Agent unterliegt derselben Rollenbeschränkung wie dein Dashboard-Account; wenn du eine Aktion nicht ausführen kannst, kann es der Agent auch nicht.