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.
wanaku-ai/wanaku
Wanaku is an MCP router that sits between AI clients and backend services. Instead of each client connecting to many servers directly, it presents a single endpoint and routes incoming requests through a filter pipeline, providing namespace isolation, tool management and MCP-to-MCP forwarding. Its most distinctive feature is the bridge role: a remote MCP server is registered as a forward with a name and an address, its tools are discovered automatically and appear in the local catalogue, and the connecting client cannot tell they come from elsewhere. A refresh call rediscovers tools from a forward when the upstream changes. Namespaces let tools, resources and prompts be organised into isolated groups, addressed as a path segment on the MCP endpoint. The router exposes three surfaces in the default layout: the MCP protocol endpoint, a management REST API providing create, read, update and delete operations over tools, resources, prompts, forwards and namespaces, and a web admin dashboard for the same objects. Forwards can be preloaded at startup from a wanaku.yaml file, or the server can start empty and be populated over the API. Authentication is optional and handled outside the process by oauth2-proxy with Keycloak, with one proxy in front of the MCP port for any authenticated user and another in front of the management port requiring an admin role; the router itself serves RFC 9728 OAuth protected resource metadata so clients can discover the authorisation server. Extensibility comes from a plugin system of feature crates and the composable filter pipeline, with a WebAssembly-based evaluator engine documented separately. It is distributed as an install script for Linux and macOS, as multi-architecture container images for x86_64 and aarch64, or built from source. The project is Apache 2.0 licensed and has a documentation site with a guided tutorial.
https://github.com/wanaku-ai/wanaku
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.
metatool-ai/metamcp
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.
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.