Haiku RAG is an intelligent retrieval - augmented generation system built on LanceDB, Pydantic AI, and Docling. It supports hybrid search, re - ranking, Q&A agents, multi - agent research processes, and provides local - first document processing and MCP server integration.

Eino is an LLM application development framework designed specifically for Golang, aiming to simplify the AI application development process through concise, scalable, reliable, and efficient component abstraction and orchestration capabilities. It provides a rich component library, powerful graphical orchestration functions, complete stream processing support, and a highly scalable aspect mechanism, covering the full-cycle toolchain from development to deployment.

Sail is a project aiming to unify stream processing, batch processing, and compute - intensive (AI) workloads. It provides an alternative to Spark SQL and Spark DataFrame APIs and supports both standalone and distributed environments.

The Crawl4AI RAG MCP Server is an AI agent service integrating web crawler and RAG functions, supporting smart URL detection, recursive crawling, parallel processing, and vector search. It aims to provide powerful knowledge acquisition and retrieval capabilities for AI coding assistants.

Awesome MCP Servers is a comprehensive collection of Model Context Protocol (MCP) servers, covering 7,158 MCP servers divided into 33 categories, including AI integration, art and media, browser automation, cloud services, databases, developer tools, file systems, finance, gaming, hardware, healthcare, infrastructure, knowledge management, location maps, marketing, monitoring, multimedia processing, operating systems, project management, scientific research, security, social media, travel and transportation, utilities, and version control, etc.

mcp-hfspace is an MCP server that connects to Hugging Face Spaces, supporting various AI functions such as image generation, speech processing, and visual models, simplifying the integration with Claude Desktop.

Clippy is a macOS terminal clipboard tool that supports copying file references, GUI pasting, management of recently downloaded files, processing of pipeline data, and AI integration with the MCP server, improving work efficiency.

HWP-MCP is a protocol service that enables AI models to control HWP documents, supporting document creation, editing, and automation processing.

Claude Talk to Figma MCP is a plugin based on the Model Context Protocol that allows AI tools such as Claude Desktop to directly interact with Figma, enabling AI-assisted design capabilities. The project connects the AI client and the Figma plugin through a WebSocket server, supporting design operations such as document analysis, element creation and modification, and text processing.

Crawl4AI MCP Server is an intelligent information acquisition server based on the MCP protocol, which provides multi - engine search and optimized web content extraction functions for AI systems, and converts web pages into a format suitable for LLM processing.

The CSV Editor is an AI - driven MCP server that provides powerful CSV data processing capabilities for AI assistants, including data cleaning, transformation, analysis, and validation, and supports auto - save and history tracking.

The MCP Document Converter is a multi-format document conversion tool based on the MCP protocol, supporting bidirectional conversion between five formats: Markdown, HTML, DOCX, PDF, and text, providing powerful document processing capabilities for AI assistants.

MarketScope AI is an intelligent healthcare market analysis platform that provides functions such as healthcare segment market analysis, product comparison, and sales data insights through AI and natural language processing technologies.

LegalContext is an open - source MCP server that securely connects the Clio document management system with the Claude AI assistant, enabling local legal document processing and retrieval.

MCP Agile Flow is an AI - assisted agile development workflow management system based on FastMCP, providing RESTful APIs and a resource - prioritized architecture, supporting natural language command processing and multi - IDE integration.

An MCP server based on OpenSCAD that generates multi - view images through AI and reconstructs them into parametric 3D models, supporting remote CUDA - accelerated processing.

An implementation of a local proxy server and client based on the MCP platform, integrating multiple AI tool functions such as weather query, Google search, camera control, image generation, and intelligent dialogue, supporting modular expansion and high-performance concurrent processing.

The Recraft AI MCP Server is a server that integrates MCP clients with Recraft AI's image processing capabilities, supporting functions such as generating and editing raster/vector images, creating custom styles, image vectorization, background processing, and image upscaling.

The Swarms API is a REST API for building, deploying, and managing multi-agent systems. It supports multiple AI models and swarm architectures, providing functions such as real-time monitoring, batch processing, and task scheduling.

A multi - functional MCP server integrating RunwayML and Luma AI APIs, supporting video/image generation and processing tasks

A lightweight server based on the Model Context Protocol (MCP), designed for image processing and cloud upload, supporting resizing, conversion, optimization, and uploading to multiple cloud storage services, suitable for AI assistants and automated workflows.

Media Gen MCP is a server that strictly follows the TypeScript and MCP specifications, focusing on generating and editing images and videos using OpenAI and Google's AI models. It provides a series of tools, including image generation/editing, video creation/remixing, file acquisition and processing, and supports intelligent resource linking and inline output. It is suitable for various MCP-compatible clients.

The OpenSCAD MCP Server is a service for generating parametric 3D models from text or images. It supports multi - view reconstruction, AI image generation, remote CUDA processing, and workflow approval, and finally outputs OpenSCAD - compatible model files.

ChatPPT is an AI - driven presentation generation service that supports generating PPTs according to themes or requirements, automatically creating PPTs by uploading documents, and provides online editing and download functions. Its MCP server supports 18 intelligent document processing APIs, covering various scenarios such as PPT production and resume analysis.

The Oxenstierna project aims to provide functions for searching, obtaining, and analyzing archive content by integrating multiple APIs (such as OAIPMH, IIIF, and Search API) of the Swedish National Archives, including the HTR (Handwritten Text Recognition) process and image processing.

PersonaLive is an AI-based real-time portrait animation system that supports real-time driving through a camera or offline video processing to generate vivid virtual avatars, suitable for scenarios such as live streaming.

The Neural Child Development System is a breakthrough artificial intelligence framework that reconstructs the learning method of neural networks by simulating human psychological development stages (including cognitive, emotional, and social growth). This system integrates developmental psychology theories (such as Piaget's cognitive development stages and attachment theory) and neuroscience principles to build a complex architecture including perceptual processing, emotional regulation, memory systems, and psychological components, aiming to create AI with real emotional intelligence and natural development capabilities.

A browser automation tool based on the MCP architecture that combines web scraping capabilities with LLM intelligence, supports Google search, intelligent web page content extraction, and AI processing, suitable for various website types.

A document indexing system based on PostgreSQL and pgvector, supporting AI - driven semantic search, including functions for crawling, processing, and querying documents.

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.

The MCP Server is an interaction system based on the Model Context Protocol standard, combining IPFS distributed storage and Claude AI processing capabilities to achieve efficient interaction between models, agents, and contextual data.

An optimized MCP protocol web scraping server that significantly reduces the token usage of AI processing through server - side HTML to Markdown conversion and CSS selector filtering, providing efficient content extraction functions.

This project implements a read-only MCP server for the Notion API, focusing on providing efficient content query and retrieval functions for AI assistants. Through optimization measures such as streamlining the toolset, parallel processing, and automatic content exploration, it significantly improves performance and solves the problem of the limited number of AI assistant tools.

Figma MCP PRO is a professional AI-optimized design analysis tool that provides a 5-step workflow for design-to-code conversion, supports 10 frameworks, and includes intelligent annotation processing and batch resource download functions.

The Stability AI MCP Server is an MCP server that integrates the image processing functions of Stability AI, supporting various image operations such as generation, editing, and enlargement.

Zed's PDF semantic search extension, integrating an AI assistant to enhance document processing capabilities

SQLite MCP Server is an enterprise-level SQLite database enhancement tool that provides 73 dedicated tools, supporting advanced analysis, JSON operations, text processing, vector search, geospatial operations, and intelligent workflow automation. It has AI-native JSON operations and enhanced security.

MCP Kling is the first and only complete Kling AI MCP server, offering 13 creative tools that support video generation, image processing, lip-syncing, and virtual try-on, enabling seamless integration with Claude, suitable for content creators and developers.

MCP image extraction and conversion service, providing local/network image processing and Base64 encoding functions for AI assistants

gbox is an open - source self - hosted sandbox project that provides a secure environment for MCP integration and other AI agent use cases. It includes tools such as a terminal, browser, and file editor, supports local task execution and file processing, and provides Python and Typescript SDKs.