Kong/kong
Kong Gateway is a cloud-native, scalable API gateway that manages API, AI LLM, and Model Context Protocol (MCP) traffic with advanced security, observability, and extensibility features.
DecoCMS is an open-source Context Management System designed to centralize and manage Model Context Protocols (MCPs) for AI applications. It provides a secure and scalable MCP Mesh that aggregates organizational context, tools, data access, and policies into a unified platform. DecoCMS enables developers to declare and compose MCPs, build AI workflows and agents, and deploy full-stack AI applications with governance, observability, and cost control. The system supports TypeScript-first development, allowing backend and frontend components to share the same codebase and types, enhancing developer productivity and consistency. The core of DecoCMS is the MCP Mesh, a distributed runtime that manages context, connections, and observability for AI agents. It offers features such as fine-grained role-based access control (RBAC), audit trails, spend caps, and full tracing of UI interactions, agent calls, and model responses. The Mesh supports secure token-based connections to external MCP servers and enables the creation of virtual MCPs, or "AI Apps," which are governed toolsets exposed to various MCP clients. DecoCMS includes an AI App Framework that leverages React and Tailwind UI to build AI-native web software, including admin interfaces, workflows, and custom views. The framework supports generative admin interfaces to assist in product requirement documentation and implementation. The platform is designed for deployment flexibility, supporting Cloudflare Workers, AWS, and local runtimes like Bun and Deno. Developers can create projects, define tools and workflows, add user interfaces, and deploy their applications with simple commands. DecoCMS emphasizes governance and FinOps with built-in authentication, authorization, auditing, and cost monitoring. It also features an extensible runtime architecture, allowing the addition of custom adapters, schemas, and MCP connectors. Overall, DecoCMS addresses the challenges faced by AI teams in managing complex AI workflows and applications by providing a unified, secure, and observable MCP-native platform that integrates development, deployment, and governance in a single system.
https://github.com/decocms/mesh
Kong Gateway is a cloud-native, scalable API gateway that manages API, AI LLM, and Model Context Protocol (MCP) traffic with advanced security, observability, and extensibility features.
Higress is a cloud-native AI native API gateway by Alibaba that supports hosting Model Context Protocol (MCP) servers, enabling unified management of AI and LLM APIs with extensible Wasm plugins and enterprise-grade features.
IBM/mcp-context-forge is a production-grade MCP Gateway that unifies and manages MCP and REST services, providing a secure, scalable, and feature-rich interface for AI clients.
mcpo is a secure and simple proxy server that exposes Model Context Protocol (MCP) tools as OpenAPI-compatible HTTP servers, enabling seamless integration with LLM agents and applications.
mcp-proxy is a proxy server tool that enables communication between MCP servers using stdio and SSE transport protocols, facilitating interoperability within the MCP ecosystem.
MetaMCP is a proxy server that aggregates multiple MCP servers into a unified MCP server endpoint, applies middleware, and hosts these endpoints for seamless integration with MCP clients.
MCPHub is a unified management platform that aggregates multiple Model Context Protocol (MCP) servers into streamable HTTP endpoints, providing centralized control, real-time monitoring, secure access, and intelligent tool discovery for efficient AI tool integration.
MCP Gateway is a lightweight, configuration-driven gateway service that converts existing APIs into MCP protocol-compliant endpoints without code changes, supporting Docker and Kubernetes deployments with a built-in management UI.