Scrapbox

Provides a notes-based MCP server with note creation, access via note:// URIs, and prompts to summarize notes.

javascript

2

GitHub Stars

javascript

Language

6 months ago

First Indexed

2 months ago

Catalog Refreshed

Documentation & install

Readme and setup notes from the catalogue, plus a client-ready config you can copy for your MCP host.

Installation

Add the following to your MCP client configuration file.

Configuration

View docs

{
  "mcpServers": {
    "yuheinakasaka-scrapbox-mcp": {
      "command": "/path/to/scrapbox-mcp/build/index.js",
      "args": []
    }
  }
}

You run a TypeScript-based MCP server that provides a simple notes system with text notes accessible via note:// URIs, and you can create and summarize notes using dedicated MCP tools. This server demonstrates core MCP concepts and lets you store, retrieve, and reason about notes through a clean, local workflow.

How to use

Use an MCP client to interact with the scrapbox notes server. You can create notes with a title and content, then access existing notes via note:// URIs. Generate a summary of all stored notes by invoking the summarize_notes prompt, which embeds all notes as resources for downstream processing. Practical tasks you can perform include creating new notes, listing existing notes, accessing note metadata, and generating a combined summary of your notes.

How to install

Prerequisites you need before installing: Node.js (version 14.x or newer) and npm.

Install dependencies and build the server with the following commands.

npm install

npm run build

Configuration and debugging

To run the server locally in development, you can use the auto-rebuild workflow to watch for changes and rebuild automatically.

If you want to debug MCP traffic, you can start the MCP Inspector tool to access debugging utilities in your browser.

npm run inspector

Available tools

create_note

Create a new text note by providing a title and content. The tool stores the note in the server state for later retrieval and processing.

summarize_notes

Generate a summary of all stored notes. This tool embeds all note contents as resources and returns a structured prompt suitable for an LLM summarization workflow.