Layerdock MCP server
Commit Oct 19, 2026Allows coding agents to read website feedback, view screenshots, and access console traces to fix bugs directly from the editor.
Also known as LayerDock/layerdock-mcp
- Stars
- 0
- Tools
- 5
- Downloads, 30 days
- —
- Latest version
- —
- Last commit
- Oct 19, 2026
- License
- MIT
What is Layerdock MCP?
Layerdock allows coding agents to read website feedback, view screenshots, and access console traces to fix bugs directly from the editor. It exposes 5 tools, such as list_docks, list_feedback, get_feedback.
Summary generated from the project's README
About Layerdock MCP server
Fixing website bugs directly from your coding editor is what layerdock-mcp enables for developers using AI agents. By connecting to LayerDock, coding agents can access website feedback, view captured screenshots, and examine console or network traces to understand reported issues. This integration works with clients like Claude Code, Cursor, Codex CLI, and Windsurf through a local configuration using a personal access token.
The server provides specific tools to manage the debugging workflow. Developers can use list_docks to see their sites, list_feedback to find open issues, and get_feedback to receive a detailed fix brief. This brief includes CSS selectors, computed styles, and even a search string designed to match source code accurately. The get_feedback tool also supports different detail levels, such as auto, minimal, or full, to manage the amount of data returned.
Beyond just reading data, the server allows agents to interact with the feedback loop. You can use update_feedback_status to move a pin through your workflow or reply_to_feedback to post comments on a thread. Any replies sent by an agent are automatically labeled to distinguish them from human responses, ensuring clear communication within your team.
What you can do with it
- 1Identify pending website bugsAsk your AI agent to find all open feedback items across all your connected sites to prioritize your work.
- 2Debug layout or behavior issuesProvide the agent with a detailed brief containing screenshots and console errors to diagnose a specific UI bug.
- 3Communicate fixes to teammatesHave the agent post a reply to a feedback thread once a bug has been addressed.
Written from the project's README. Every use case is checked against a quote from it.
Layerdock MCP tools 5
Detected from the READMElist_dockslist_feedbackget_feedbackupdate_feedback_statusreply_to_feedback
| list_docks | — | |
| list_feedback | — | |
| get_feedback | — | |
| update_feedback_status | — | |
| reply_to_feedback | — |
Configuration
LAYERDOCK_TOKEN
| Name | Description | |
|---|---|---|
| LAYERDOCK_TOKEN | — |
Automated checks
Ran Nov 14, 2026Full report →Not verified yet. A server needs a score of 80, no serious finding, and enough data for us to check. How checks work · What to fix for more points
- Source repository linked and reachablelayerdock/layerdock-mcp is public and reachablegithub.com/layerdock/layerdock-mcp ↗Pass
- Package names this repository as its sourceNot checked
- Build provenance (Sigstore attestation)Not checked
- Open source license (OSI)MITspdx.org/licenses/MIT.html ↗Pass
- Commit or release in the last yearLast commit or release 2026-10-19github.com/layerdock/layerdock-mcp ↗Pass
- OpenSSF ScorecardNot checked
- Package name not close to a popular packageNot checked
- No critical advisory in the package or its dependenciesNot checked
- No hidden instructions to the model5 tool descriptions and the README read; no override phrases, credential paths or hidden charactersPass
- Destructive tools are labelledNo tool named like delete, drop or execPass
- Remote endpoint answers the MCP handshakeNot checked
README
View on 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
Layerdock MCP questions
What tools does Layerdock MCP provide?
It exposes 5 tools, including list_docks, list_feedback, get_feedback, update_feedback_status, reply_to_feedback.
What information is included in a feedback brief?
The brief includes the reporter's request, the component or source file, a matching search string, page URL, CSS selectors, computed styles, console errors, and a screenshot.
Can the agent perform actions I am not authorized to do in the dashboard?
No, the agent is subject to the same role gating as your dashboard account; if you cannot perform an action, the agent cannot either.