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 Go is a server-side framework for the Model Context Protocol (MCP) implemented in Go, used to connect LLM applications with external data sources and tools. It provides core functions such as resource management, tool invocation, and prompt templates, and supports session management and middleware extension.

The AWS MCP Servers are a set of dedicated servers based on the Model Context Protocol, offering various AWS-related functions, including document retrieval, knowledge base query, CDK best practices, cost analysis, image generation, etc., aiming to enhance the integration of AI applications with AWS services through a standardized protocol.

Browser MCP is an MCP server + Chrome extension that enables browser automation through AI applications (such as VS Code, Claude, etc.). It features fast response, privacy protection, staying logged in, and avoiding detection.

Provide MCP server support for Nuxt/Vite applications to help models better understand the application structure.

Opik is an open-source LLM evaluation framework that supports tracking, evaluating, and monitoring LLM applications, helping developers build more efficient and cost-effective LLM systems.

mcpo is a simple and easy-to-use proxy tool that can quickly convert any MCP tool into an OpenAPI-compatible HTTP server, enabling access through standard RESTful interfaces and facilitating integration with LLM agents and applications.

Coco AI is a unified search platform that integrates enterprise applications and data (such as Google Workspace, Dropbox, GitHub, etc.), providing cross-platform search and AI-driven team chat functions, aiming to improve work efficiency and collaboration experience.

This is a curated list of Web3 Model Context Protocol (MCP) servers, covering multiple categories such as chain interaction, trading, DeFi, market data, tools, and social. MCP is an open protocol that standardizes how applications provide context to LLMs, similar to the USB - C port for AI applications. DeMCP is the first decentralized MCP network, focusing on providing self - developed and open - source MCP services for agents, supporting cryptocurrency payments, and redefining the security and reliability of MCP by combining TEE and blockchain registries.

The DeepSeek MCP server project provides anonymous API proxy services for applications such as Claude Desktop, supporting multi-turn conversations and automatic model switching.

The Google Workspace MCP Server is a comprehensive multi - client protocol server that controls the full suite of Google office applications such as Calendar, Drive, Gmail, and Docs through natural language. It supports one - click installation on the Claude desktop, providing advanced OAuth authentication and service caching.

emcee is a tool that provides a Model Context Protocol (MCP) server for any web application with an OpenAPI specification, connecting applications such as Claude Desktop to external tools and data services.

The DeepSeek MCP Server is a model context protocol server designed for the DeepSeek API, supporting seamless integration with MCP-compatible applications such as Claude Desktop, providing anonymous API access and intelligent conversation management.

A prototype of the MCP server based on Uber Eats, enabling seamless integration between LLM applications and external tools

Chroma is an open-source vector database that provides memory support for Python and JavaScript LLM applications, supporting multiple client types and document operations.

The ClickUp MCP Server is a model context protocol server for integrating ClickUp tasks with AI applications, supporting task, space, list, and folder management through a standardized protocol.

A secure code sandbox environment based on Docker containers, providing an isolated execution space for AI applications.

This project provides an MCP server for deploying code to Google Cloud Run services, supporting deployment from various sources such as AI-assisted IDEs, AI assistant applications, and proxy SDKs.

The Next.js MCP Server is a tool for analyzing and extracting API route information from Next.js applications.

Obsidian's MCP Tools plugin provides AI applications with the ability to securely access the knowledge base

This project provides a series of Model Context Protocol servers based on Quarkus/Java to extend the capabilities of MCP-enabled LLM applications, including various services such as JDBC database interaction, JVM monitoring, and file system operations.

This project is a server - side implementation based on the Model Context Protocol (MCP), providing seamless integration with the Milvus vector database and enabling multiple LLM applications such as Claude Desktop and Cursor to access database functions through a standardized protocol.

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.

The GPT Researcher MCP Server is an AI research server based on the MCP protocol. It can provide high-quality and optimized research results for LLM applications through in-depth web search and verification.

An MCP server that enables LLM applications to interact with macOS through AppleScript, providing a standardized interface to control various system functions.

The Maigret MCP Server is an MCP protocol server that provides services for the OSINT tool maigret. It supports searching for usernames across social networks and analyzing URLs and can be integrated into applications such as Claude Desktop.

The Code Runner MCP Server is an MCP service that supports the execution of multi - language code snippets. It can directly run code and display results in applications such as VS Code.

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.

Open Data MCP is an open - source project aiming to quickly connect public data sets to LLM applications through the MCP protocol. The project provides a CLI tool to achieve a 2 - minute connection (currently supporting Claude) and establishes a community collaboration framework that allows developers to easily contribute and publish public data sets. The core goal is to build an infrastructure that connects all LLM applications with millions of public data sets.

Open Data MCP is an open - source project aiming to quickly connect public data sets to LLM applications through the MCP protocol, enabling convenient access to open data and community - based publishing.

The ClickUp MCP Server is a model context protocol server for integrating ClickUp tasks with AI applications. It supports managing tasks, spaces, lists, folders, etc. through a standardized protocol and provides functions such as time tracking and tag management.

A secure Docker container code sandbox environment that provides an isolated execution space for AI applications, supporting multiple programming environments and file operations.

This project is an MCP server for deploying code to Google Cloud Run, supporting deployment through AI agents, IDEs, and assistant applications.

BrowserTools MCP is a powerful browser monitoring and interaction tool that enables AI applications to capture and analyze browser data through Chrome extensions and a local Node server, and is compatible with multiple MCP clients.

cutterMCP is a model context protocol server designed for LLMs for autonomous reverse engineering applications.

MCPHub is an embeddable Model Context Protocol (MCP) solution for AI service integration. It provides a unified way of configuration and management, supports multiple AI frameworks (such as OpenAI Agents, LangChain, Autogen), and simplifies the connection between MCP servers and AI applications.

The StrawHat AI development repository provides a complete solution for building local and online AI development environments, including various tools such as the Ollama backend, Open - WebUI frontend, and Claude desktop proxy, supporting rapid deployment and development of AI applications.

Raygun's MCP server provides access to the API V3 endpoints for Crash Reporting and Real User Monitoring applications.

The Telegram MCP Server is a Node.js-based service that allows LLMs to send notifications and receive user responses via Telegram and supports integration with MCP-compatible applications such as Cline.

This project implements a server based on the Model Context Protocol (MCP) for deploying web applications to AWS serverless infrastructure, supporting automatic deployment of front - end, back - end, and full - stack applications.