Agent-to-agent communication is the next frontier of AI infrastructure. As teams decompose monolithic AI workflows into specialized agents — a research agent, a booking agent, a summarization agent — the calls between those agents become as important to govern as the calls from end users. With…
[](/blog/product-releases/kong-ai-gateway-3-14)
Kong Agent Gateway is a new capability within Kong AI Gateway that extends our platform to more robustly cover agent-to-agent (A2A) communication. With this release, Kong AI Gateway now natively handles all three patterns of AI traffic in a product that is already being used by some of the largest…
[](/blog/product-releases/kong-agent-gateway)
The Demo-to-Production Gap Production reality multiplies complexity exponentially. In production, you need: Multi-tool orchestration with different authentication methods Robust retry logic with exponential backoff and circuit breakers Performance under load with multiple concurrent AI agents…
[](/blog/enterprise/build-vs-buy-mcp-server-infrastructure)
The CLI case is real Let's start with the strongest version of the CLI argument. For well-known tools baked into model training data (e.g., git, grep, curl, jq, docker, kubectl, gh, etc.), CLIs are highly effective for agent workflows. The model already knows the flags and the output formats. And…
[](/blog/enterprise/cli-vs-mcp-enterprise-ai-governance)
Tool discovery for AI agents In early agent implementations, tools are often statically configured inside the agent. For example: { "mcpServers": { "weatherServer": { "command": "uv", "args": "run", "weather_server.py" ] }, "githubServer": {…
[](/blog/engineering/mcp-registry-dynamic-tool-discovery)
We have crossed a threshold in the AI economy where the competitive advantage is no longer about access to data — it’s about access to context. The "context economy" has arrived, defined by a fundamental shift from selling data products to selling context products as a service. This is the shift…
[](/blog/enterprise/the-platform-enterprises-need-to-compete)
AI agents are spreading across organizations rapidly. Each agent needs secure access to different Model Context Protocol (MCP) servers. Authentication becomes complex. Scaling creates bottlenecks. The dreaded "too many endpoints" problem emerges. You face a classic AI infrastructure headache. The…
[](/blog/learning-center/what-is-a-mcp-gateway)
Agents are ultimately decision makers. They make those decisions by combining intelligence with context, ultimately meaning they are only ever as useful as the context they can access. An agent that can't check inventory levels, look up customer history, or verify pricing isn't autonomous — it's…
[](/blog/product-releases/introducing-kong-context-mesh)
MCP servers expose all tools by default. There are two problems with this: security (agents get capabilities they shouldn't have) and performance (too many tools degrade LLM tool selection). The solution? Put a gateway between agents and MCP servers that filters tools based on who's asking. Default…
[](/blog/engineering/mcp-tool-governance-security-meets-context-efficiency)
The Kong MCP Registry acts as a central directory for AI agents and clients to access services that provide context or take action. For AI agents, think of it as a combination of a "Service Catalog" and a "Developer Portal." It offers the metadata, API endpoints, and capability definitions that…
[](/blog/product-releases/kong-mcp-registry-tech-preview)
The example below shows how an AI agent can be built using Volcano SDK with minimal code, while still interacting with backend services in a controlled way. The agent is created by first configuring an LLM, then defining an MCP (Model Context Protocol) endpoint that represents a promotions service.…
[](/blog/engineering/secure-ai-agents-volcano-sdk-kong-mcp-proxy)
MCP is an open standard that defines how AI clients communicate with remote servers. It provides a standardized protocol for clients like Claude, Cursor, or VS Code to access tools, resources, and capabilities from external systems. Currently, MCP servers can expose several types of capabilities to…
[](/blog/engineering/mcp-servers-guide)
If you've used KAi before, you'll notice the difference immediately. The enhanced version has deeper access to your Konnect environment and new tools for debugging, analytics, and configuration management: The new KAi is more capable because it's backed by a structured set of tools that can query…
[](/blog/product-releases/kai-upgrade-powered-by-konnect-mcp-server)
The report identifies a mindset trap that's holding most organizations back: "inside-out" integration thinking. Inside-out means viewing integration from the perspective of only prioritizing the reuse of legacy integrations and architecture (i.e., simply wrapping existing integrations with MCP and…
[](/blog/enterprise/gartners-context-mesh)
Kong Insomnia 12.3 TL;DR? Your New Year’s resolution is probably something along the lines of “work smarter, not harder.” Our resolution is to make that actually possible. Insomnia 12.1 and 12.2 sharpened your tools, and now Insomnia 12.3 removes the friction to allow you to focus on building great…
[](/blog/product-releases/insomnia-12-3)
The evolution of AI agents and autonomous systems has created new challenges for enterprise organizations. While securing API endpoints is well-understood, controlling access to individual AI agent tools presents a unique authorization problem. Today, we're excited to announce a powerful solution…
[](/blog/product-releases/mcp-tool-acls-ai-gateway)