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.
YAMCP is a command-line tool for organising MCP servers into local workspaces, called yams. Instead of configuring every AI application with every server, a user registers servers once and groups them into workspaces by purpose, such as coding, design or research, or by the client that will consume them, such as Cursor, Claude or Windsurf. Running a workspace starts a local gateway: a single MCP server that connects to each member server, over stdio or SSE, and re-exposes their capabilities through one endpoint, so a client needs only one configuration entry. The tool is installed globally from npm as yamcp or run through npx. Its commands split into three groups. Server commands add a server interactively, list the configured servers and their status, remove one, or import several at once from a JSON configuration file whose format matches the bundled example. Yam commands create a workspace interactively, list workspaces or show the details of a named one, edit an existing workspace, scan it and delete it. The run command starts the gateway for a named workspace, and the log command prints where communication logs are stored. Centralised logging is one of the stated reasons for the project: traffic from every server lands in one store, so debugging no longer means digging through each client application's separate log files. The architecture, sketched as a Mermaid diagram in the README, has the CLI managing a configuration store of providers and workspaces, and an McpGateway combining a GatewayServer that speaks stdio to the AI app with a GatewayRouter that connects out to the workspace servers, both writing to a shared logger. A separate community project, YAMCP UI, adds a web dashboard over the same configuration. The code is TypeScript.
https://github.com/hamidra/yamcp
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.