Skip to content
MCP server

layernote

Pull client design feedback into Claude and coding agents, and close it out

Install
Pricing
Free trial
Platforms
Web, API, CLI
Runs
Locally or Remotely
Version
0.11.1
Listing updated
2 days ago

About layernote

layernote is an MCP server for design and media. It can run locally on your machine or as a hosted remote server.

Layernote collects client comments pinned on live sites, Figma frames, PDFs, images and video. This server hands those comments to an AI agent, so nobody has to copy feedback into a prompt. For each comment the agent receives the page URL and CSS selector of the element, the full thread and an element screenshot it can look at.

The workflow named on the site: the agent lists open feedback with list_feedback, opens each item with get_feedback, fixes it in the user's repository, then closes it with add_feedback_comment and resolve_feedback. The site counts twenty tools in total, covering reading projects, comments, files and Figma frames, acting on pins, replies, assignees, due dates and statuses, and setting up a project, Figma screens, uploads and a share link.

A connection belongs to one person and one workspace and reaches only the projects that person can reach. Claude on the web and desktop connects by URL, Claude Code by URL or token, and Codex and Cursor with a token. Tokens are stored hashed and can be revoked under Settings, AI access, and workspace admins can see every connection. Comments written by Claude are marked as AI.

Install

Run in a terminal

claude mcp add --transport http mcp https://app.layernote.io/mcp

Add to Settings → Connectors → Add custom connector

https://app.layernote.io/mcp
Install in CursorOpens Cursor, which asks you to confirm. Or add it by hand:

Add to ~/.cursor/mcp.json

{
  "mcpServers": {
    "mcp": {
      "url": "https://app.layernote.io/mcp"
    }
  }
}
Install in VS CodeOpens VS Code, which asks you to confirm. Or add it by hand:

Add to .vscode/mcp.json

{
  "servers": {
    "mcp": {
      "type": "http",
      "url": "https://app.layernote.io/mcp"
    }
  }
}

Add to ~/.codeium/windsurf/mcp_config.json

{
  "mcpServers": {
    "mcp": {
      "serverUrl": "https://app.layernote.io/mcp"
    }
  }
}

Add to your client's MCP settings (most use this shape)

{
  "mcpServers": {
    "mcp": {
      "type": "http",
      "url": "https://app.layernote.io/mcp"
    }
  }
}

Configuration

  • LAYERNOTE_TOKENA personal token from layernote: Settings, AI access.Required
  • LAYERNOTE_API_URLOnly for a self-hosted or non-production layernote.

Tools this server provides (4)

Taken from the project documentation; the running server may differ.

list_feedback
Finds the open comments on a page.
get_feedback
Opens one comment with its selector and screenshot.
add_feedback_comment
Adds a reply to a comment thread.
resolve_feedback
Marks a comment as resolved.

What it does

Selector and screenshot context
Each comment comes with the page URL, CSS selector, thread and element screenshot.
Comment-to-fix loop
An agent lists open comments, fixes the code, replies and resolves them.
Review in chat
In Claude on web and desktop, files open in a viewer with comments as pins.
Project setup
Claude can create a project, import Figma screens and return a share link.
Named, revocable tokens
Tokens are stored hashed and revoked in Settings, AI access.
Admin visibility
Workspace owners and admins see every token and connected app.

Good for

  • Fix every open comment on a homepage from a coding agent
  • Summarise open client feedback on a project
  • Review a PDF or Figma frame with Claude and pin comments on it
  • Set up a client review project and share link from chat
  • Report back to clients with replies and status changes on each item

Pricing

Free trial, from $19 a month

No free tier; 14-day trial. Solo $19/mo, Studio $49/mo, Team $89/mo; clients review for free

Prices change. Check layernote.io before you buy.

layernote FAQ

Which clients can use it?

Claude on web and desktop, Claude Code, Codex and Cursor. Other MCP clients connect by URL, or with a token and the npx command.

Do I need a token?

Not for Claude: add the connector URL and sign in. Codex, Cursor and other tools use a token created under Settings, AI access.

Does it cost extra?

AI access is included in the Solo, Studio and Team plans while the workspace plan is active.

Is my code sent anywhere?

The site says code is never sent anywhere; with a token the server runs on your machine, by URL it runs on layernote's side.

Does it need its own AI subscription?

No. It only supplies data and actions to the agent you already run and pay for.

Is layernote free?

layernote is a paid product with a free trial. Paid plans start at $19 a month.

How do I add layernote to Claude Code?

Run this command in your terminal: claude mcp add --transport http mcp https://app.layernote.io/mcp

What are the best alternatives to layernote?

The closest alternatives to layernote are REA, HyperFrames by HeyGen, Codebase Memory, GitHub and Serena MCP: the IDE for your agent.

Alternatives to layernote

  1. REA

    MCP server

    CLI and MCP server that lets coding agents reverse engineer apps and binaries

    Runs locally
    • Open source
    • 464K GitHub stars
    • Developer tools
  2. Hosted MCP connector for creating and rendering videos from HTML through AI chat

    • Remote
    • Freemium
    • 85.3K GitHub stars
    • Design and media
  3. Codebase Memory

    MCP server

    Local MCP server that builds a code knowledge graph for AI coding agents

    Runs locally
    • Open source
    • 48.7K GitHub stars
    • Knowledge and memory
  4. GitHub

    MCP server

    Official MCP server connecting AI assistants to GitHub repos, issues and workflows

    Not checked yet
    • Remote
    • Open source
    • 34.5K GitHub stars
    • Developer tools
  5. MCP toolkit giving coding agents symbol-level code retrieval and editing

    Runs locally
    • Open source
    • 31.5K GitHub stars
    • Developer tools
  6. XERJ

    MCP server

    Local search engine for AI agents with cited answers over your code and docs

    Runs locally
    • Open source
    • 19.2K GitHub stars
    • Knowledge and memory