Document Processing MCP Repositories

Integrate real-time spell checking and correction capabilities into applications to enhance text accuracy and clarity. Offers seamless integration with existing workflows for instant feedback on spelling errors.

Integrates data scraping, content processing, and AI capabilities, with features for document conversion, web scraping, and knowledge management. Supports real-time information access through various data APIs and secure code execution.

Converts PDF files to structured Markdown format while preserving the original layout. Supports batch processing of local files and URLs for efficient handling of multiple documents.

Captures screenshots and performs OCR text recognition on macOS. Supports both Japanese and English text, offering multiple output formats.

Search and retrieve structured data from BookStack pages with customizable queries, pagination, and HTML-to-text conversion for enhanced reading. It includes robust error handling and validation for seamless content access.

This utility functions as a Model Context Protocol (MCP) gateway, specifically designed to facilitate interaction with digital assets managed by the Eagle application suite. Analogous to broader document processing, which strives to transform physical media into digitally intelligible information through tasks like layout analysis and optical character recognition, this server enables programmatic management of digital collections. It supports operations including organization structure modification, retrieval of descriptive metadata, and handling of multimedia resources via a standardized interface.

Extracts video metadata and captions from YouTube videos, converting them into customizable markdown formats. Supports multiple languages and offers search functionality within captions.

Search and retrieve documents from Outline knowledge bases, facilitating access to internal documentation. Supports secure access via interactive credentials and environment variables.

Interact programmatically with Microsoft Word documents, automating common Word processing tasks using a simple MCP interface. Facilitates document manipulation capabilities via COM Interop on Windows.

Manage Excalidraw drawings using a straightforward API, providing capabilities to create, update, retrieve, and delete drawings. Export drawings in multiple formats such as SVG, PNG, and JSON while utilizing a simple file-based storage system.

Export and permanently save WeChat chat records, allowing users to view messages such as images, videos, and files even if WeChat no longer supports them.

Manage and search documentation using advanced semantic search and retrieval-augmented generation capabilities. Supports document management tasks such as adding, listing, and deleting documents with automatic text chunking and vector storage through Qdrant.

Enable seamless interaction with Coda documents, including listing, creating, reading, updating, and duplicating pages. Provides command access to manipulate document content directly within an AI framework.

Manage and semantically search documentation by adding, ingesting, chunking, and querying notes across various document types. Create summaries tailored to specific detail levels and access individual notes through a custom URI scheme.

Crawl websites to create AI-powered search capabilities that enhance content discoverability and interaction with AI language models.

Analyzes Japanese and English texts by counting characters and words and evaluating linguistic features such as average sentence length and lexical diversity. Supports input via file paths or direct text input, accommodating both absolute and relative paths.

Fetches and stores documentation in a vector database for semantic search and retrieval, enhancing LLM capabilities with relevant documentation context. Supports adding documentation from URLs or local files and querying with natural language.

Automates the creation of standardized documentation by extracting information from various source files and applying templates. Integrates with Google Drive and GitHub to enhance documentation processes with AI-generated content and management features.

Lists all available MCP services configured in Claude Desktop, providing easy access for reference and copying. Keeps the list dynamically updated and accessible from the tools menu for quick selection.

Automated web accessibility scanning using Playwright and Axe-core, enabling WCAG compliance checks and annotated screenshot capture. Generates detailed accessibility reports and interacts with web pages through browser automation.

Dify allows users to build and test AI workflows on a visual canvas, facilitating the integration of tools and data sources for enhanced AI interactions. It supports both cloud hosting and self-hosting options for flexible usage.

Provides intelligent text summarization to condense output and reduce token usage, preventing potential crashes during extensive tasks.

Integrates with Google Drive for listing, reading, and searching files, and facilitates reading and writing to Google Sheets. Provides access to Google Drive content and spreadsheet data for various applications.

Read and write Microsoft Word (docx) files with capabilities to edit paragraphs and insert new text. Access complete document content, including tables and images, through a command-line interface.

Showcase and highlight professional qualifications and achievements through a structured resume format. Allows users to effectively communicate their experiences to potential employers.

A specialized MCP server for writing text to the Textwell application on macOS, offering modes for replacing, inserting, or appending text. It facilitates text manipulation directly within the Textwell environment.

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.

Manage and query documents in a local directory using retrieval-augmented generation techniques, integrating context from text files and Git repositories. Supports listing documents and generating responses based on queries with context from the stored content.

Create and manipulate PowerPoint presentations programmatically, enabling the generation of slides, exporting to PDF, and retrieving metadata seamlessly.

Facilitates access to Figma files and prototypes, enabling integration of design assets directly into AI coding environments. Streamlines design workflows by connecting AI agents with Figma's design resources.