Kong Introduces MCP Registry in Kong Konnect to Power AI Connectivity for Agent Discovery and Governance

New capability in Kong Konnect Catalog makes Kong the unified platform for governing and discovering MCP-native AI tools at enterprise scale

NEW YORK, February 2, 2026 — Kong Inc., a leading developer of API and AI connectivity technologies, today announced Kong® MCP Registry, a new enterprise directory within the Kong Konnect Catalog designed to register, discover and govern MCP servers and AI native tools for agentic applications. Kong MCP Registry integrates with the Model Context Protocol (MCP) ecosystem while remaining compliant with the broader AI Alliance Interoperability Framework (AAIF) standard, enabling Kong Konnect to serve as a centralized system of record for approved internal and external tools used by AI agents. 

Because Kong Konnect already serves as the system of record for enterprise APIs, MCP Registry operates as an extension of Kong's existing API Catalog. This enables organizations to govern MCP servers in full operational context, including their underlying API dependencies, ownership, blast radius, and inherited policies. By linking MCP servers directly to the APIs that they are built on, Kong enables enterprises to manage agent tools with the same rigor applied to mission-critical application infrastructure. This provides deeper visibility, stronger governance, and tighter control that any standalone registries can provide. 

“With Kong MCP Registry, we are extending the Konnect Service Catalog to give enterprises a secure and scalable way to operationalize MCP, ensuring agents can safely discover and use approved tools while maintaining enterprise grade governance, visibility and control,” said Marco Palladino, Co-Founder and Chief Technology Officer at Kong. “This builds on Kong’s AI Gateway and other AI connectivity capabilities in Konnect, giving enterprises the infrastructure they need to move from fragmented AI experiments to production-ready, governed AI systems that can securely connect models, agents, APIs and tools at scale.”

Today’s announcement is part of Kong’s AI Connectivity launch at the New York Stock Exchange, streamed live, where Kong is introducing a new category of infrastructure designed to help enterprises move from fragmented AI experiments to production scale systems. Kong’s leadership team will be outlining the company’s roadmap for AI Connectivity and the strategic importance of this new category within AI infrastructure, and how Kong Konnect is evolving to support routing, governance, discovery and monetization of AI and agentic workloads in production. 

Enterprises are moving fast on agentic AI, but many are struggling to get from pilots to durable production systems. S&P Global reports that 42% of companies abandon AI initiatives before production, often because speed exposes hidden friction across cost, governance, and operational complexity. Kong’s AI Connectivity roadmap is designed to unify and govern the full AI data path so organizations can scale AI with sustainable velocity, predictable cost control, and enterprise-grade risk management.

As enterprises scale their AI initiatives, organizations face growing challenges in safely enabling AI agents to discover and use internal and external tools. Today, MCP connections are often configured manually, hardcoded and managed in isolation across teams, creating fragmented integrations, increased operational risk and limited visibility.

Modern AI applications such as personalized AI assistants or recommendation engines often require agents to securely connect to multiple internal systems and tools in real time. For example, a global digital media company may need to access real time user signals, call internal recommendation and content APIs, invoke large language models to generate personalized responses, and coordinate across multiple specialized agents. With Kong MCP Registry, enterprises can centrally register and govern the MCP servers that power these tools, enabling agents to dynamically discover approved capabilities while maintaining consistent security, ownership, and policy controls across the full AI data path. With MCP Registry, Konnect becomes a unified API and AI platform capable of managing the full lifecycle of AI connectivity, from LLM routing and AI gateway traffic to multi-agent communication and centralized discovery for MCP-native tools. 

Accelerating AI while reducing risk and cost

Kong MCP Registry is designed to help enterprises move faster with AI while reducing operational risk and improving reliability and cost efficiency. With MCP Registry, organizations can:

• Accelerate AI initiatives by enabling faster time to market and reducing integration costs through automated and self-service discovery of MCP servers for developers and agents
• Reduce risk and help ensure compliance by reducing shadow AI and providing audit trails and visibility needed to support regulatory requirements, such as GDPR, HIPAA and the EU AI Act
• Control AI deployment costs and improve reliability through centralized visibility into tool usage, health and failures, enabling faster troubleshooting and confident retirement of unused or underperforming MCP servers

Kong MCP Registry also provides:

• Dynamic discovery through a centralized enterprise catalog where AI agents can discover available MCP servers, endpoints and capabilities without hardcoded configurations
• Trusted tools by allowing only approved MCP servers and tools to be discovered and used, with clear ownership, metadata and policy-based controls
• Observability with centralized visibility into tool usage, health and failures across MCP servers for monitoring, cost management and optimization

Kong MCP Registry establishes Konnect as the enterprise system of record for AI tool discovery and governance. Kong MCP Registry will be available in tech preview as part of Kong Konnect beginning this month, with additional Dev Portal and secure access capabilities expected to follow.

Source: S and P Global Market Intelligence, 451 Research, Generative AI experiences rapid adoption, but with mixed outcomes, Voice of the Enterprise AI and Machine Learning Use Cases 2025, published May 30, 2025.