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.
metatool-ai/metamcp
MetaMCP is a proxy server designed to aggregate multiple Model Context Protocol (MCP) servers into a single unified MCP server endpoint. It allows dynamic grouping of MCP servers into namespaces, enabling seamless integration and management of these servers through a consolidated interface. MetaMCP acts as an MCP server itself, making it compatible with any MCP client, thus facilitating easy plug-and-play usage. The project supports middleware application at the namespace level, which intercepts and transforms MCP requests and responses. This feature allows for enhanced observability, security, and optimization of tool contexts for large language models (LLMs). MetaMCP also provides an inspector tool similar to the official MCP inspector but with saved server configurations, enabling developers to debug and inspect MetaMCP endpoints efficiently. MetaMCP supports various use cases such as grouping MCP servers into namespaces, hosting them as meta-MCPs with public endpoints, and applying authentication strategies. It supports SSE and Streamable HTTP transports and offers OpenAPI endpoints for clients like Open WebUI. The project is compatible with MCP tools, resources, prompts, and OAuth-enabled MCP servers. The architecture includes a Next.js frontend, an Express.js backend with tRPC, and uses a standalone monorepo with Turborepo and Docker for deployment. It addresses the cold start problem by pre-allocating idle sessions and allows customization of Dockerfiles to reduce startup times. Authentication mechanisms include session cookies and API key authorization. MetaMCP is intended as infrastructure for hosting dynamically composed MCP servers and building agents on top of them. It is open-source under the MIT license and encourages contributions. The project roadmap includes plans for headless admin API access, more middlewares, chat/agent playground, and testing for MCP tool selection optimization. Keywords: Model Context Protocol, MCP, proxy server, middleware, MCP server aggregation, namespaces, MCP endpoints, SSE, Streamable HTTP, OpenAPI, authentication, inspector, MCP clients, dynamic MCP hosting, tool context optimization, LLM, Docker, Next.js, Express.js, tRPC, monorepo, Turborepo, MIT license.
https://github.com/metatool-ai/metamcp
Also in Gateways
alibaba/higress
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
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.
open-webui/mcpo
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.
sparfenyuk/mcp-proxy
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.
samanhappy/mcphub
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-ecosystem/mcp-gateway
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.
mcpjungle/MCPJungle
MCPJungle is a self-hosted MCP server registry and gateway that centralizes the management and discovery of MCP servers and tools for AI agents and organizations.