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.
mcpo is a secure and simple proxy server designed to expose Model Context Protocol (MCP) tools as OpenAPI-compatible HTTP servers. This enables seamless integration of MCP tools with large language model (LLM) agents and applications that expect OpenAPI servers. Unlike native MCP servers that communicate over raw stdio, which is inherently insecure, incompatible with many tools, and lacks standard features like documentation, authentication, and error handling, mcpo addresses these issues by providing a secure, stable, and scalable solution using trusted web standards. mcpo works instantly with OpenAPI tools, SDKs, and user interfaces, auto-generating interactive documentation for every tool without requiring any configuration. It uses pure HTTP, eliminating the need for sockets or glue code, making the integration process straightforward and hassle-free. The project supports various MCP server types, including standard command-based servers, SSE-compatible servers, and streamable HTTP-compatible servers, allowing flexible deployment options. Users can run mcpo with simple commands, specifying ports, API keys for security, and server types as needed. It also supports running multiple MCP tools via a single configuration file, with each tool accessible under its unique route and accompanied by its dedicated OpenAPI schema and proxy handler. This makes mcpo a versatile and powerful tool for making AI tools usable, secure, and interoperable. The project is developed in Python and recommends using the 'uv' tool for fast startup and zero configuration. It is open-source under the MIT license and encourages community contributions. mcpo provides a modern approach to bridging MCP tools with the broader ecosystem of OpenAPI-compatible applications, enhancing usability and security while simplifying deployment and integration.
https://github.com/open-webui/mcpo
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.
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.
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.