Scrapbox AI Assistant

An MCP server that connects Scrapbox data to Claude Code for advanced knowledge management and creative support.

typescript

2

GitHub Stars

typescript

Language

5 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": {
    "yoheitabo-scrapbox-ai-assistant": {
      "command": "node",
      "args": [
        "/path/to/scrapbox-ai-assistant/dist/index.js"
      ],
      "env": {
        "SCRAPBOX_CONFIG_PATH": "/path/to/scrapbox-config.json"
      }
    }
  }
}

This MCP Server bridges your Scrapbox data with Claude Code to enable intelligent knowledge management, creative support, and knowledge extraction at scale. It provides fast search, relationship analysis, theme extraction, and structured prompts to assist writing and thinking across your Scrapbox pages.

How to use

You connect to the Scrapbox MCP Server from your MCP client and use its built-in tools to search, analyze, and synthesize your Scrapbox data. Practical workflows include searching pages with filters, analyzing how pages relate to each other, and extracting themes or patterns from large data sets. You can also apply literary analysis or creative prompts to support writing projects.

How to install

Prerequisites: ensure you have Node.js and npm installed on your system. You can verify by running node -v and npm -v in your terminal.

Clone the MCP server repository:

git clone https://github.com/yourusername/scrapbox-ai-assistant.git
cd scrapbox-ai-assistant

Install dependencies and build the project:

npm install
npm run build

Prepare the demo configuration (copy the example to the working config):

cp scrapbox-config.example.json scrapbox-config.json

Start the demo server:

npm start

Additional setup notes

Prepare data by exporting your Scrapbox pages as JSON and placing the file in the configured data path. If you are dealing with large datasets, you may split the JSON into parts to improve performance.

Available tools

search_pages

Advanced search and filtering across Scrapbox pages to locate relevant content quickly.

analyze_connections

Analyze page relationships and build a knowledge network from your Scrapbox data.

extract_themes

Identify themes and patterns across a large dataset to surface insights.

literary_analysis

Provide literary analysis capabilities to support creative writing and critique.

creative_continuation

Assist in continuing creative writing projects with AI prompts and prompts chaining.

knowledge_synthesis

Synthesize knowledge from multiple Scrapbox pages into coherent summaries.