Open source MCP gateway provides advanced security, tool federation, and streamlined development for Artificial intelligence (AI) teams integrating MCP-compatible tools with AI agents.

Solo.io announced MCP Gateway, a Model Context Protocol (MCP) gateway aimed at enhancing the integration and governance of AI agents within the ecosystem of cloud native applications. Currently utilized by organizations like Domino’s Pizza and ParkMobile for API traffic management, the MCP Gateway allows for simplified deployment of advanced AI use cases as demands for managing AI workloads and traffic from Large language model (LLM) providers increase.

MCP, originally developed by Anthropic, is establishing itself as the standard for AI agent-to-tool interoperability. As its adoption expands, many leading technologies are becoming available as MCP-compatible tool servers, enabling AI clients to manage a growing array of tools more efficiently.

The MCP Gateway facilitates the discovery, security, and federation of multiple MCP tools into a virtualized MCP server. This allows developers a unified access point to a centralized tool registry regardless of the number of tools in use.

Keith Babo, Chief Product Officer at Solo.io, remarked, “While MCP has rapidly emerged as the de facto standard protocol for accessing tools from agents, building MCP integration capabilities into every application client and agent is error-prone and cumbersome for AI development teams. MCP Gateway eliminates the need to manually connect these agents and tools by consolidating MCP servers into one place, saving teams countless hours and eliminating undifferentiated heavy lifting.”

Key functionalities include automated discovery and registration of MCP tool servers, a centralized registry for developers, access to MCP tools via a single endpoint, and enhanced security measures for multi-tenant environments.

The MCP Gateway, as part of kgateway and an open source project under the Cloud Native Computing Foundation, aims to provide a comprehensive solution for integrating AI tools with robust traffic management.