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.
MCP Gateway and Registry is a self-hosted platform that puts a single governed endpoint in front of many Model Context Protocol servers. The gateway is an Nginx reverse proxy in which every registered MCP server is mounted as a separate path, so an agent framework creates one MCP client per path against the same host, for example a weather server and a currenttime server under the same gateway domain. Because the proxying happens at the HTTP layer, both SSE and Streamable HTTP transports are supported, and backend servers can live anywhere: locally on the gateway instance, in an Amazon EKS or EC2 cluster, or behind Amazon API Gateway with AWS Lambda functions. The registry component sits alongside the gateway and answers the discovery problem. It offers both a web interface and a programmatic interface for browsing which MCP servers and which individual tools an organisation has approved, so developers can find the right tool for an agent and agents themselves can look up and then invoke tools they were not originally built around. Together the two parts target the enterprise concerns the README lists: how approved servers are found, how access to them is centralised and secured, how the right tools are selected when hundreds of servers exist, and how new tools reach existing agents. Deployment instructions cover Amazon EC2 for simple setups and Amazon EKS for production, and the project is written mainly in Python with a static registry front end. The repository is archived and no longer maintained: development moved to agentic-community/mcp-gateway-registry, which carries the current features, fixes and support. This copy is useful chiefly as the original reference architecture for a path-based MCP gateway.
https://github.com/aarora79/mcp-gateway
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.