An intelligent document chunking MCP server optimized for Claude context windows. Split large documents into meaningful, context-aware chunks that can be progressively processed by Claude.
Claude Chunks helps you process large documents (like books, theses, or long papers) by:
- Breaking them into meaningful sections
- Generating rich summaries of each section
- Maintaining context and connections between sections
- Formatting output for optimal Claude context reuse
# Clone the repository
git clone https://github.com/vetlefo/claude-chunks.git
cd claude-chunks
# Install dependencies
npm install
# Build the project
npm run build
- Add to Claude Desktop config:
{
"mcpServers": {
"claude-chunks": {
"command": "node",
"args": ["/path/to/claude-chunks/dist/index.js"]
}
}
}
- Restart Claude Desktop
- Use the
chunk_document
tool in your conversations
- Basic MCP server setup
- Smart document chunking
- Section summarization
- Context preservation
- Multiple document formats
- Custom chunking strategies
- Enhanced metadata tracking
- Claude-optimized formatting
- Cross-reference tracking
- Technical term extraction
- Theme detection
- Progressive loading
Contributions are welcome! Please see our Contributing Guide for details.
MIT