Content Creation MCP Repositories

Search for YouTube videos and analyze their content by generating summaries, retrieving subtitles, and pinpointing specific video segments. The tool supports keyword-based searches and provides detailed video metadata, intelligent subtitle selection, and content analysis powered by GPT.

Collects and organizes information about the DeepSeek language model, presenting updates and insights in an e-book format. Features include compiling weekly updates and monthly summaries on technical progress, application cases, comparisons, and community news.

Download and summarize public Substack posts by extracting titles, authors, subtitles, and content directly within workflows.

This server provides a structured, hands-on course for building Generative AI applications, focusing on practical skills in Python and TypeScript. It encompasses various AI concepts and tools through 21 comprehensive lessons.

Connects to the Art Institute of Chicago's art collection, enabling searches of artworks by title, full text, or artist, and retrieves detailed information including images.

Access the Metropolitan Museum of Art's collection through natural language queries to search for artworks and retrieve detailed information on various departments.

Analyzes YouTube videos using the Gemini Vision API to extract insights such as descriptions, summaries, and key moments. Enhances video interactions by providing information and answers to user inquiries.

Define and utilize custom prompts in markdown format to streamline interactions with Claude. The server enables flexible, template-based prompt creation, incorporating enhanced error handling and seamless transport configurations.

Interact with a Strapi CMS instance through a standardized interface, managing content types and performing REST API operations, including media uploads. Built-in validation and version compatibility features enhance content management capabilities.

Enables retrieval and processing of web content by fetching web pages and converting HTML to markdown for easier manipulation. Supports content extraction in chunks from specified starting indices to facilitate information retrieval from larger documents.

Connects to Figma's API for extracting design components, styles, and text, while facilitating design system analysis and UI content management. Supports generating documentation for developers and allows AI integration for design workflow enhancement.

Extracts node hierarchies from Figma files, enabling analysis of file structures. Supports both REST API and MCP protocol with configurable node tree depth.

Provides access to Contentful's Delivery API to query and retrieve content entries, assets, and content types using natural language. It enables management of text notes and generation of summaries based on retrieved content.

Fetch and manage RSS feeds with caching and filtering capabilities. Integrates seamlessly with LLMs to provide access to the latest articles from various sources.

Integrates with Ghost CMS features, providing programmatic access to post, page, tag, author, and member management functionalities, along with image upload support.

Generates well-formatted LLM prompts from a codebase by converting its entire structure. Allows customization of output through templates to streamline code analysis and generation tasks.

Analyzes images and videos by providing URLs or local file paths, allowing for detailed insights and descriptions of the content. Uses the Gemini 2.0 Flash model for high-precision recognition and can evaluate relationships between multiple visual inputs.

Enhance your README.md files effortlessly by analyzing and resolving content conflicts with Ollama. Automatically update your documentation while ensuring consistency and clarity. Streamline your project documentation process with intelligent suggestions and conflict resolution.

An AI chatbot built with Next.js that supports advanced routing, server-side rendering, and multi-provider large language model (LLM) integration. It offers secure chat history and user data storage with customizable options using an AI SDK and modern UI components.

Connects to MCP clients to display desktop notifications on Windows 10 and macOS using customizable parameters such as title, message content, and display time. Utilizes win10toast for Windows notifications and osascript for macOS notifications, supporting both synchronous and asynchronous requests.

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

Enables interactive user input requests during AI model generation, facilitating a dynamic exchange with the user. Integrates with MCP-compatible clients to present input prompts via a simple GUI dialog box.

Control FreeCAD directly from the desktop, enabling integration with Claude Desktop for enhanced design workflows and automation. Supports various design tasks including creating flanges, toy cars, and converting 2D drawings into 3D models.

Integrates with the Typecast API to manage voices, convert text to speech, and play audio. Provides a standardized MCP interface for seamless interaction with voice capabilities.

Combines DeepSeek's reasoning capabilities with Claude 3.5 Sonnet's advanced response generation for enhanced contextual understanding and output. Utilizes a two-stage processing approach to integrate structured reasoning into detailed responses.

Integrates Figma with Cursor to retrieve design data, optimize JSON size, and convert designs into organized CSS styles for improved development workflows.

Generates and converts vector and raster images using advanced AI models with support for multiple formats. Provides flexible storage options and automatic formatting for efficient image processing.

Summarizes code files in a directory while respecting `.gitignore` rules and skips irrelevant directories. Outputs detailed summaries to a text file and supports integration with LLM tools via an MCP server.

Create and modify wireframes for modern applications using prompts. Integration with AI services like Claude Desktop and Cursor enhances the wireframing process.

Integrates DeepSeek's structured reasoning capabilities with Claude 3.5 Sonnet's advanced response generation through a two-stage processing approach. This server facilitates enhanced conversational interactions by combining deep reasoning with comprehensive output generation.