Microsoft MCP Gateway
Microsoft MCP Gateway is an open source reverse proxy and management layer for Model Context Protocol (MCP) servers that enables scalable, session-aware routing, lifecycle management, and centralized control of MCP services, especially in Kubernetes environments. It functions as a control plane that routes AI agent (MCP client) requests to the appropriate backend MCP servers with session affinity, dynamically handling multiple tools and endpoints under one unified gateway while ensuring authorization and observability. It lets teams deploy, update, and delete MCP servers and tools via RESTful APIs, register tool definitions, and manage these resources with access control layers such as bearer tokens and RBAC. Its architecture separates control plane management (CRUD operations on adapters/tools and metadata) from data plane routing (streamable HTTP connections and dynamic tool routing), offering features like session-aware stateful routing.
Learn more
ContextForge MCP Gateway
ContextForge MCP Gateway is an open source Model Context Protocol (MCP) gateway, registry, and proxy platform that provides a unified endpoint for AI clients to discover and access tools, resources, prompts, and REST or MCP services in complex AI ecosystems. It sits in front of multiple MCP servers and REST APIs to federate and unify discovery, authentication, rate-limiting, observability, and traffic routing across diverse backends, with support for transports such as HTTP, JSON-RPC, WebSocket, SSE, stdio, and streamable HTTP, and can virtualize legacy APIs as MCP-compliant tools. It includes an optional Admin UI for real-time configuration, monitoring, and log visibility, and is designed to scale from standalone deployments to multi-cluster Kubernetes environments with Redis-backed federation and caching for performance and resilience.
Learn more
Prefect Horizon
Prefect Horizon is a managed AI infrastructure platform within the broader Prefect product suite that lets teams deploy, govern, and operate Model Context Protocol (MCP) servers and AI agents at enterprise scale with production-ready features such as managed hosting, authentication, access control, observability, and tool governance. It builds on the FastMCP framework to turn MCP from just a protocol into a platform with four core integrated pillars, Deploy (host and scale MCP servers quickly with CI/CD and monitoring), Registry (a centralized catalog of first-party, third-party, and curated MCP endpoints), Gateway (role-based access control, authentication, and audit logs for secure, governed access to tools), and Agents (permissioned, user-friendly agent interfaces that can be deployed in Horizon, Slack, or exposed over MCP so business users can interact with context-aware AI without needing MCP technical knowledge).
Learn more
agentgateway
agentgateway is a unified gateway platform designed to secure, connect, and observe an organization’s entire AI ecosystem. It provides a single point of control for LLMs, AI agents, and agentic protocols such as MCP and A2A. Built from the ground up for AI-native connectivity, agentgateway supports workloads that traditional gateways cannot handle. The platform enables controlled LLM consumption with strong security, usage visibility, and budget governance. It offers full observability into agent-to-agent and agent-to-tool interactions. agentgateway is deeply invested in open source and is hosted by the Linux Foundation. It helps enterprises future-proof their AI infrastructure as agentic systems scale.
Learn more
