Chomper Document Parser

Example Use Cases

• 1

  Parse and analyze documents in multiple formats including PDF, DOCX, and emails.

• 2

  Semantic chunking and token-optimized output for efficient retrieval and processing.

• 3

  Extract metadata, images, and perform batch processing of documents.

Description

Chomper is an MCP server and Python library designed to parse a wide variety of document formats, extracting text, metadata, images, and semantic chunks optimized for retrieval-augmented generation (RAG) systems. It supports smart token management, multiple output formats including a token-optimized TOON format, and batch processing, making it ideal for AI applications requiring efficient and rich document analysis. The server also provides built-in MCP prompts for document summarization, entity extraction, and Q&A.