Genkit is an open-source framework for building AI-driven applications, providing Node.js and Go libraries, supporting the integration of multiple AI models and vector databases, and including development tools and a plugin ecosystem.

MCP Toolbox for Databases is an open-source database MCP server focusing on enterprise-level and production quality, simplifying tool development and providing complex functions such as connection pool and authentication.

Klavis AI is an open-source project that provides a simple and easy-to-use MCP (Model Context Protocol) service on Slack, Discord, and Web platforms. It includes various functions such as report generation, YouTube tools, and document conversion, supporting non-technical users and developers to use AI workflows.

The Solana Agent Kit is an open-source toolkit for connecting AI agents to the Solana protocol, supporting more than 60 blockchain operations.

Container Use is an open-source tool that provides a containerized isolated environment for coding agents, supporting parallel development of multiple agents without interference.

ACI.dev is an open-source AI agent tool infrastructure that provides multi-tenant authentication, permission management, and dynamic discovery functions for over 600 pre-integrated tools. It supports calls through a unified MCP Server or a lightweight SDK, simplifying the development of production-level AI agents.

The Quarkus Model Context Protocol (MCP) Server is an open-source protocol server that supports easy integration of LLM applications with external data sources and tools through declarative and programmatic APIs.

mcp-chat is an open-source and general-purpose MCP client tool for testing and evaluating MCP servers and proxies. It supports command-line interaction and web mode, can connect to various MCP servers (JS/Python/Docker), and provides functions such as chat history recording, model selection, and system prompt customization to help developers debug MCP services.

The Vantage MCP Server is an open-source tool that helps users query and analyze cloud cost data through natural language interaction. It serves as a bridge between the Vantage API and AI assistants, providing intuitive cost analysis capabilities and supporting integration with multiple MCP clients.

MCP is an open-source protocol for standardizing LLM interactions, providing a unified framework for connecting data sources, obtaining context, using tools, and executing standard prompts. Project examples demonstrate how to build MCP servers and clients to implement knowledge base chatbot functionality.

An MCP server integrated with the ClimateTriage API, providing tools to search for open-source issues related to climate change and sustainable development.

This project compiles a list of popular Model Context Protocol (MCP) servers based on Smithery.ai usage data. MCP is an open-source standard developed by Anthropic for establishing secure two-way connections between data sources and AI tools.

MacPilot CLI is an open-source tool that enables large language models to interact with the macOS system through the MCP protocol, providing system operation functions.

LOTUS-MCP is an open-source model coordination protocol that integrates the two major AI models, Mistral and Gemini, providing a unified interface, context sharing, and tool integration to achieve intelligent routing and cost optimization.

The ZeroPath MCP Server is an open-source project that allows developers to query security findings such as SAST issues, secrets, and patches using natural language, and directly integrate them into AI-assisted tools. It simplifies the process of handling security issues, providing security context directly in the development environment without the need for manual dashboard or ticket management.

A TypeScript bridge project connecting local LLMs to MCP servers, providing a web interface that enables open-source models to use tool capabilities similar to Claude, supporting functions such as file system operations, web search, and complex reasoning.

The Codex MCP Tool is an open-source MCP server that connects the IDE or AI assistant to the Codex CLI, supporting non-interactive automation, secure sandbox editing, and large-scale code analysis. It provides progress streaming updates and a structured change mode.

Lspace is an open-source API backend and server that implements the Model Context Protocol (MCP), helping developers transform insights from AI conversations into a searchable and persistent knowledge base and integrate it into various tools.

defold-mcp is an open-source Model Context Protocol (MCP) server designed to connect the Defold game engine with modern developer tools and AI-assisted workflows. It provides a set of automation tools for managing Defold projects, generating scripts and resources, debugging and analyzing projects, and supports integration with AI development tools such as Cursor.

The Amazon Ads API MCP SDK is an open-source toolkit that enables AI applications to securely interact with the Amazon Advertising API through the Model Context Protocol. It supports multi-region and comprehensive API coverage and is used to build AI-driven advertising management applications.

Grasp is an open-source and self-hostable humanized browser automation tool that supports the MCP and A2A protocols and can seamlessly integrate with various AI applications. Through Docker containerization deployment, it provides a browser operation experience controlled by natural language.

MacPilot CLI is an open-source tool that allows large language models to interact with the macOS system through the MCP protocol, providing system operation functions.

MCP over SSE is an open-source library that implements the Model Context Protocol based on Server-Sent Events. It provides a complete MCP server functionality, including SSE connection management, JSON-RPC message processing, tool registration and execution, and session management.

The MCP DigitalOcean integration is an open-source project that provides cloud resource management and operation interfaces based on the DigitalOcean API, supporting operations on various resources and tools.

The first open-source MCP server that enables full-featured AI control of a remote macOS system without the need to install additional software, providing complete desktop operation capabilities.

The Model Context Protocol (MCP) is an open-source protocol that provides a series of reference implementations and community-built servers, enabling large language models (LLMs) to access tools and data sources securely and controllably. The project includes implementations of various functional servers, covering areas such as file systems, databases, search, and API integration, and supports development with TypeScript and Python SDKs.

The Model Context Protocol (MCP) is an open-source protocol designed to enable Large Language Models (LLMs) to seamlessly interact with external tools, services, and data sources through a standardized interface, simplifying the integration process and expanding AI capabilities.

The Model Context Protocol (MCP) is an open-source protocol that provides a series of reference implementations and community-built servers, enabling large language models (LLMs) to access tools and data sources securely and controllably. This project includes various types of server implementations, covering multiple domains such as file systems, databases, Git, and Slack, and supports TypeScript and Python SDKs.

MCP is an open-source AI-driven penetration testing framework that integrates multiple security tools, analyzes their outputs in real-time, strictly follows the standard penetration testing process, and provides intelligent assistance to security testers.

gbox is an open-source self-hosted sandbox project that provides a secure execution environment for AI agents, supports various tools such as terminals, browsers, and file operations, and is compatible with the MCP protocol.

Neon MCP Server is an open-source tool that allows users to interact with Neon Postgres databases through natural language, simplifying database management tasks such as creating projects, branches, queries, and migrations.

The Tavily MCP Server is an open-source tool based on the Model Context Protocol (MCP) that provides real-time web search and data extraction capabilities for AI systems such as Claude. It supports seamless integration with multiple MCP clients (such as Cline, Cursor, and Claude Desktop), enabling AI assistants to access Tavily's advanced search and content extraction functions.

Tavily MCP is an open-source project that enables AI systems to seamlessly connect to Tavily's search and data extraction tools through the Model Context Protocol (MCP) standard, providing AI assistants like Claude with the ability to access real-time web information. The project offers search, extraction, mapping, and crawling tools and supports multiple client configurations.

Velero MCP Server is an open-source model context protocol server that provides read-only, secure, and structured access to Velero backup and scheduling resources in a Kubernetes cluster for AI tools.

Model Context Protocol (MCP) is an open-source protocol that provides a series of reference implementations and community-developed servers, enabling large language models (LLMs) to securely and controllably access tools and data sources. The project includes various types of server implementations covering multiple domains such as file systems, databases, Git, and Slack, demonstrating the diversity and scalability of MCP.

Ultra-MCP-Servers is an open-source project that enables users to create and manage their own Model Context Protocol (MCP) servers. It offers a variety of tool and service integrations, such as YouTube transcription, cloud storage, web crawlers, etc., and encourages community contributions.

An unofficial Reclaim.ai MCP server that allows MCP-compatible clients to interact with the Reclaim API through standard resources and tools, supporting 14 operations such as task management and timing.

A small tool that improves the accuracy of WeChat QR code recognition through two-stage detection. First, use YOLOv8 to locate the position of the QR code, and then use the WeChat open-source model to extract the content.

Easy-MCP-Use is an open-source TypeScript library designed to connect any LLM to any MCP server and build custom agents with tool access rights. It supports multiple LLM models and MCP servers, providing functions such as dynamic server selection, multi-server support, and tool restrictions, enabling developers to easily connect LLMs to various tools.

MCP-Use is an open-source library that allows developers to connect any LLM that supports tool calls to an MCP server and build custom agents with tool access capabilities.