Document Processing MCP Repositories

Interact with on-disk documents through retrieval-augmented generation (RAG) and hybrid search capabilities in LanceDB.

Build intelligent, document-based applications with integrated data retrieval capabilities, leveraging Retrieval-Augmented Generation (RAG) methodologies.

Automates the process of assigning diagnosis and procedure codes from electronic health records. Utilizes advanced models to improve accuracy and efficiency in medical coding tasks, with tools and datasets from MIMIC-III and MIMIC-IV.

Create custom tools to interact with large language models, facilitating web content fetching and processing of various document formats including PDF, Word, and Excel. Supports advanced features such as OCR for image content in documents and enhances workflow automation.

Collects and documents code from projects into markdown, providing tools for code analysis and documentation.

Manage, analyze, and visualize knowledge graphs with support for various graph types, including ontologies and timelines. Integrate effectively with MCP-compatible AI assistants to query and manipulate knowledge graph data while tracking resource management and version status.

Manage Confluence wiki pages by creating, updating, deleting, and searching them through a unified interface. Automatically selects the relevant knowledge base based on user queries to enhance content management efficiency.

TypeScript-based MCP server that provides a system for creating and managing text notes, allowing access to notes via URIs along with metadata. It includes functionality for generating summaries of notes and listing note resources.

Facilitates document manipulation across Microsoft Word, Excel, and PDF formats, enabling editing, creation, and conversion of various document types seamlessly.

Manage markdown documentation by creating, reading, updating, and deleting files while analyzing their health and improving quality. Enhance AI assistants' interactions with documentation through natural language processing capabilities.

Generate and deploy modern static websites efficiently, with features for live reloading during development and seamless deployment to GitHub Pages or other static hosting services. Provides an extensible framework for website management and content generation.

Fetches up-to-date, version-specific code documentation and examples from source libraries to enhance prompts, reducing reliance on outdated code and inaccurate APIs. Integrates real-time library documentation into LLM context to improve coding accuracy and productivity.

Fetches and indexes documentation for various software libraries, packages, and APIs. Provides powerful search capabilities to enable AI systems to access the latest official documentation from multiple sources.

Edit files using a TypeScript MCP server, based on Anthropic's filesystem editing tools. It facilitates direct file manipulation while working with MCP protocols.

Query and manipulate Notion Pages by creating, reading, and updating content directly from prompts. Seamlessly manage Notion databases and enhance productivity through integration.

Scrapes documentation from web URLs and converts it into markdown format, saving the converted documentation to a specified output path. Integrates with the Model Context Protocol (MCP) for enhanced data management.

Crawl, index, and manage documentation while enabling full-text search across various document formats for efficient information retrieval. Integrates with AI to enhance document access and management capabilities.

Retrieve and manage PDF documents stored in AWS S3. Offers access to S3 buckets and their objects, enabling data retrieval for integration with AI models.

Diffs and patches JavaScript objects and arrays, enabling change tracking and state reversion through a simple API.

Read and analyze binary files, extracting metadata and structure from various binary formats, including Unreal Engine assets. The server features an extensible architecture for adding support for new binary formats as needed.

Upload documents in PDF or CSV formats and perform natural language queries to retrieve relevant information. It features document segmentation and embedding storage using a Chroma vector store for efficient retrieval.

Manage and manipulate text files through a standardized API, enabling operations like viewing, editing, and creating files in various directories.

Integrate with the Box API to perform file operations, including file search, text extraction, and AI-based querying. Manage and process Box data efficiently with advanced AI capabilities.

Enables optical character recognition for Chinese, English, and numbers using pre-trained models or custom training. Provides powerful text recognition capabilities for a variety of applications.

Comprehensive document processing capabilities including reading various document formats and converting them to different formats. Provides features for PDF manipulation such as merging and splitting, alongside document conversion tools.

Converts various file formats to Markdown using the MarkItDown utility, enabling seamless processing of PDFs, Office documents, images, audio, HTML, and more into Markdown format.

Fetches npm package documentation from multiple programming ecosystems and presents it for use with LLMs, such as Claude, without the need for API keys.

Provides intelligent query generation and documentation assistance using Claude AI by analyzing API documentation. Delivers tools for generating queries from natural language requests and retrieving relevant documentation information based on user questions.

Manage and manipulate Feishu documents with capabilities for creating, editing, and extracting structured and unstructured content, along with rich text formatting and code block handling.

Facilitates the creation and editing of Microsoft Word documents via a straightforward API. Supports adding formatted text, images, and tables, enabling document generation and modification through natural language commands with LLM integration.