# Document Processing

This project is a document processing server based on the Model Context Protocol (MCP) standard. By building a vector database and an MCP interface, it enables AI assistants to access external document resources and break through the knowledge limitations of large language models. The project includes two major components: a document processing pipeline and an MCP server. It supports multiple embedding models and file formats and can be applied to scenarios such as querying the latest technical documents and understanding private code libraries.

An MCP server that provides comprehensive document processing capabilities

A Python-based document processing and Retrieval Augmented Generation (RAG) server that uses the DuckDB database to store embedding vectors, supports multiple file format processing, and provides a Web interface and API.

A Docx document processing service based on the FastMCP library, supporting the creation, editing, and management of Word documents through an AI assistant

A DOCX document processing MCP server based on the mammoth library, providing functions such as text extraction, HTML conversion, structural analysis, image extraction, and Markdown conversion, supporting full - format retention and document analysis.

An MCP server that provides unstructured document processing capabilities, supports multiple file formats, and helps LLMs extract and utilize document content.

The Feishu MCP Server is a service based on the Model Context Protocol that provides Feishu API integration, enabling AI models to easily interact with Feishu services.

DevDocs is an intelligent document crawling and processing tool designed to help developers quickly understand and implement technical documents, significantly shortening the R & D cycle.

The Pinecone MCP Server is a model context protocol server designed for Claude Desktop, providing read and write interaction capabilities with Pinecone indexes.

The MCP Docling Server is a server that provides document processing capabilities, supporting various document conversions and extraction functions, including format conversion, table extraction, and Q&A generation. It can be integrated with the Llama Stack to enhance the capabilities of LLM applications.

An MCP server that enhances the functionality of the Qdrant vector database, providing functions such as collection management, document addition, and semantic search.

An AI Word document processing server based on the MCP protocol, providing document creation, editing, and management functions

The Feishu MCP Plugin is a service that connects Feishu with AI coding tools (such as Cursor), providing functions such as document reading, message sending, and contract approval.

The MCP server for handwritten OCR, providing functions such as document upload, status check, and text retrieval

The Feishu MCP Plugin is a service that connects Feishu with AI coding tools (such as Cursor), providing functions such as document reading, message sending, and contract approval, and supporting operation through self - built application authorization.

Axiomatic MCP servers provide AI assistants with an advanced tool suite for scientific computing, document processing, and photonic circuit design.

The MCP server for handwriting OCR, which integrates with the Handwriting OCR API and supports uploading image/PDF documents, checking status, and obtaining OCR recognition results.

A repository containing a variety of practical MCP services, providing services such as Git, Google Sheets, Jenkins, and file operations, along with development tutorials

MCP Server for Handwritten OCR

An MCP service tool for downloading documentation websites and preparing RAG indexes