This project is an implementation of an MCP server integrated with the Sonar API, providing real-time web search capabilities for Claude. It includes guides on system architecture, tool configuration, Docker deployment, and multi-platform integration.

The MCP-Framework is a TypeScript-based framework for elegantly building Model Context Protocol (MCP) servers. It provides an out-of-the-box architecture, supports automatic directory discovery of tools, resources, and prompts, and has multiple transmission methods and type-safe features.

wcgw is an MCP server project that integrates Shell and code editing tools, allowing AI to execute commands, read and write files, edit code, etc. on the local machine. It provides multiple modes (such as Architect Mode, Code Writing Mode, etc.), supports task checkpoint saving, terminal interaction, syntax checking, etc., and is suitable for scenarios such as code development and problem troubleshooting.

The MCP server and CLI tool of Anna's Archive are used to search for and download documents on the platform and support access through an API key.

The AI Development Assistant MCP Server is an AI - based code development toolkit that provides functions such as code architecture generation, UI screenshot analysis, and code review, specifically designed for Cursor.

Blueprint MCP is a chart generation tool based on the Arcade ecosystem. It uses technologies such as Nano Banana Pro to automatically generate visual charts such as architecture diagrams and flowcharts by analyzing codebases and system architectures, helping developers understand complex systems.

napi is a tool developed by NanoAPI, aiming to automatically analyze software architecture complexity, support extracting functional modules from the codebase, provide both CLI and UI operation methods, and be compatible with mainstream CI/CD platforms to help developers optimize architecture design.

ATLAS is an intelligent task and knowledge management system built on TypeScript and Neo4j, designed for LLM agents, providing a three - layer management architecture for projects, tasks, and knowledge.

Pipelock is an open-source AI agent firewall that provides security protection with zero runtime dependencies through a single binary file. It adopts an architecture with separated capabilities and deploys a nine-layer scanning pipeline between the agent and the Internet to prevent secret leakage, prompt injection, and malicious tool calls. It supports multiple proxy modes (Fetch proxy, forward proxy, WebSocket proxy) and MCP proxy, and provides functions such as an emergency stop switch, audit logs, and SIEM integration.

The Figma MCP Server project integrates with the Figma API through clients such as Claude, supports file reading and design system management functions, has an extensible architecture but is currently read - only due to API limitations.

The Zen7 Payment Agent is the first practical implementation of a DePA decentralized payment agent. It adopts a multi - agent collaborative architecture, supports the A2A and MCP protocols, and provides multi - chain and multi - currency payment solutions for AI agents and Dapp applications, enabling automated cryptocurrency payments and LLM - driven intent recognition.

DB MCP Server is a multi-database supported server that implements the Model Context Protocol (MCP) and provides AI assistants with the ability to access databases in a structured manner. It supports MySQL and PostgreSQL, can connect to multiple databases simultaneously, automatically generates dedicated tools, and follows a clear architecture design.

A meta - function architecture server that supports AI to dynamically create and execute custom tools

MCP-Diagram is a server tool that quickly generates various types of diagrams (such as architecture diagrams, UML diagrams, etc.) from text descriptions. It supports integration with AI assistants like Claude.

CortexGraph is an MCP server that provides a human-like memory system for AI assistants. It realizes the natural decay and reinforcement use of memories by simulating the Ebbinghaus forgetting curve, including short-term memory storage, long-term memory archiving, and knowledge graph functions.

This project demonstrates a real-time multi-tool agent architecture based on LangGraph and the MCP protocol. By decoupling agent orchestration and tool execution, it realizes a modular and scalable AI system. The MCP service supports multiple transport protocols (SSE/STDIO), allows AI agents to dynamically call remote tools, and has cross-language and cloud deployment capabilities.

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.

Memory MCP is an MCP server that provides persistent memory for AI assistants. Through a two - tier architecture of hot cache and cold storage, it enables zero - latency automatic injection of high - frequency knowledge and semantic search, allowing Claude to remember project contexts and reduce repeated explanations.

Pincer-MCP is a security-hardened MCP gateway that protects the API keys of AI agents through a proxy token architecture, ensuring that agents can only use proxy tokens and cannot access real keys. It supports various AI services and GPG signing tools.

rag - mcp is an over - designed retrieval - augmented generation system that provides multiple text search modes (semantic search, question - answer search, style search) through a Python server. It uses PostgreSQL and pgvector to store text embedding vectors, supports interaction with AI agents, and has a complex but scalable architecture.

ToolBox is an AI-driven automated tool development platform that provides modular architecture, AI-assisted tool generation, enterprise-level service integration, and real-time update functions.

Vibe Marketing MCP is an open - source marketing content generation server that integrates the best social media hooks, copywriting frameworks, and KOL archetypes to help AI clients generate more human - friendly and platform - optimized marketing content.

Octocode MCP is an advanced AI code assistant that provides intelligent search and discovery functions across the GitHub and npm ecosystems. It helps developers quickly understand codebases, analyze project architectures, discover security patterns, and supports enterprise-level security and cross-platform use.

An AI note application based on the MCP protocol, supporting a dual-server architecture and DynamoDB storage

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.

Archon is an intelligent system for autonomously constructing and optimizing AI agents. It demonstrates key principles of modern AI through iterative development, including agent reasoning, domain knowledge integration, and scalable architecture. The current version V4 provides a comprehensive Streamlit interface, supports Docker deployment, and integrates with MCP services for seamless docking of the AI IDE.

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.

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.

A high-performance Python implementation of the MCP server, focusing on memory optimization and infrastructure component tracking, supporting Claude Desktop integration but archived due to specification issues.

A free cryptocurrency news API that provides real-time news aggregation from over 200 sources. No API key is required, and it supports AI analysis, multi-language translation, and historical archives.

tldraw-agent is an AI-based text-to-chart generation tool that supports multiple usage methods such as command line, library, and MCP service, and can automatically generate text descriptions (such as architecture diagrams and flowcharts) into charts in PNG or SVG format.

MCP Architect is a service that provides comprehensive architecture expertise, supporting multiple architecture fields through professional agents, resources, and tools.

A multi-platform job aggregation service based on the MCP architecture, supporting the acquisition and standardization of job data from mainstream recruitment websites and providing structured support for large models.

Grigori is a desktop application that helps developers manage and organize programming specifications, architectural patterns, and development preferences through the MCP protocol, enabling AI programming assistants to access personalized coding contexts.

The Arc MCP Server is a Model Context Protocol server that simplifies framework deployment, focusing on shared hosting environments, supporting multi - platform deployment and guided operations.

Provide a programming interface for the IACR Cryptology ePrint Archive, supporting efficient retrieval of cryptographic research papers

The Malaysia Open Data MCP service provides convenient access to government datasets and collections, supporting enhanced unified search, Parquet file parsing, hybrid data access architecture, and multi - provider geocoding functions.

This project builds a natural - language - based WhatsApp message sending and scheduling system through a client - server architecture. The server uses Mistral's LLM to parse user intentions and calls Twilio's API to send WhatsApp messages.

mcp - scaffold is a development sandbox for verifying the Model Context Protocol (MCP) server, providing support for local LLMs (such as LLaMA 7B) and cloud inference, including a chat interface and reference architecture.

The GoHighLevel MCP server is a fundamental project aiming to connect the GoHighLevel community with AI automation through the Model Context Protocol (MCP). It provides access to all sub - account level GoHighLevel API endpoints, supports 269 tools, covering multiple functional categories such as contact management, messaging, sales pipelines, and calendar appointments. The project emphasizes community collaboration, an open architecture, and educational resources, while also reminding users to pay attention to key issues such as AI security, rate limits, and data security.