layerdock-mcp
OfficialServer Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| LAYERDOCK_TOKEN | Yes | Required. Your personal access token (ldk_...). | |
| LAYERDOCK_API_URL | No | Optional. Defaults to https://www.layerdock.io. Point it at a local dev server when working on LayerDock itself. | https://www.layerdock.io |
Instructions
Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.
This server publishes no instructions, or was last inspected before Glama recorded them.
Capabilities
Features and capabilities supported by this server
Protocol revision2025-11-25
| Capability | Details |
|---|---|
| tools | {
"listChanged": true
} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| list_docksA | List the LayerDock docks (sites) you have access to, with any codebase hints their owner declared (framework, source root, CMS). Call this to get a dockId — but note that list_feedback no longer requires one, so "what is open across everything?" is a single call. |
| list_feedbackA | List feedback pins. Omit dockId to see open work across EVERY dock you can reach — that is the one call that answers "what needs my attention?". Pass dockId to scope to one site. Returns a lean summary; call get_feedback for the full fix brief of the one pin you pick. |
| get_feedbackA | Get one feedback pin as a complete fix brief: WHERE it is (page URL, section, CSS selector, the component name when the framework exposed it), a SEARCH STRING that actually matches source (one contiguous run of literal text, not the element's whole innerText), WHAT the reporter wants changed, the SCREENSHOT as an image when one was captured, and the DEBUG state at the moment of capture (console errors and failed/slow requests, each stamped with how long before capture it happened). The brief tells you when a screenshot was NOT captured rather than sending you looking for one. Call this before changing any code. |
| update_feedback_statusA | Move a pin through the workflow: open, in_review, changes_requested, approved, resolved. Call this after you have actually made the fix. Your permission to set a given status depends on your role on the dock; the server rejects what you are not allowed to do. |
| reply_to_feedbackA | Post a reply on a pin's thread. It is attributed to the person who owns this token AND labelled as coming via a coding agent, so the reviewer can tell your claim from that person's own — the server stamps both from the authenticated token. Do NOT sign the message text yourself; that is duplicated, and unlike the server-side stamp it is not something the reviewer can trust. Use this to say what you changed before resolving the pin, so a silent status flip does not leave them guessing. |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
TDQS
Scored across 5 tools
Each tool targets a clearly distinct operation: list_feedback retrieves pins across docks, list_docks retrieves sites, get_feedback retrieves one detailed brief, update_feedback_status changes workflow state, and reply_to_feedback posts a message. Descriptions explicitly clarify boundaries (e.g., lean summary vs. full brief, server-side stamping) leaving no realistic misselection.
All names use snake_case with a consistent verb_noun pattern: list_feedback, list_docks, get_feedback, update_feedback_status, reply_to_feedback. The minor prep in reply_to_feedback does not break the overall predictable convention.
Five tools are well-scoped for an agent that fixes feedback pins: see open work, find a dock, get the fix brief, update status, and reply. No tool feels redundant or missing for the stated purpose.
The surface covers the full agent workflow: discover open pins (list_feedback), resolve dock context (list_docks), retrieve all fix details (get_feedback), change lifecycle state (update_feedback_status), and communicate with the reviewer (reply_to_feedback). No obvious dead ends for the coding-agent use case.