Kong Introduces MCP Gateway and Volcano SDK for Agentic AI Development
Kong Inc. announced in a press release new support for the Model Context Protocol (MCP) and agentic AI development at API Summit 2025. The company introduced a next-generation enterprise MCP gateway in its AI Gateway, an MCP-enabled Konnect Developer Portal, and a new open-source software development kit called Volcano.
The updated AI Gateway includes automatic MCP server generation from Kong-managed APIs, centralized authentication through an MCP OAuth 2.1 plugin, and enhanced observability features for monitoring MCP tools and workflows. These updates are intended to improve security and governance across enterprise AI agent deployments.
The MCP-enabled Konnect Developer Portal allows organizations to turn their portals into MCP servers, enabling discovery and access for AI coding assistants. New tools such as the AI Integration Composer and AI Integration Runner allow developers to compose and execute MCP-based integrations within the same secure infrastructure.
Kong also introduced Volcano, an open-source SDK designed to simplify the creation of MCP-powered AI agents. Volcano provides a lightweight framework for building, testing, and deploying agentic applications that integrate with APIs and MCP servers managed through Kong Konnect. The SDK is available on GitHub and aims to accelerate AI agent development with improved security and interoperability.
We hope you enjoyed this article
Consider subscribing to one of our newsletters like AI Programming Weekly or Daily AI Brief.
Also, consider following us on social media:
AI Programming Weekly
Weekly news about AI tools for software engineers, AI enabled IDE's and much more.
Whitepaper
Tensordyne Napier: What If One Rack Could Do the Work of Nine?
Tensordyne
This Tensordyne whitepaper presents Napier, an inference-focused AI processor and rack-scale system based on the company’s TDN Math logarithmic number system. It examines infrastructure requirements for large mixture-of-experts and agentic models, compares major inference architecture approaches, and details the TDN AIP processor, TDN72 pod, TDN Link fabric, and Napier Ultra configuration. The paper reports simulation-based performance, cost, and accuracy-validation results, including Tensordyne’s projected comparison of one Napier rack with a nine-rack Nvidia Rubin plus Groq deployment; the chip is reported as taped out and in fabrication.
Read moreYou may also like
Knack Launches HIPAA Compliant MCP Server for AI App Builders
Gates Foundation Joins Agentic AI Foundation
Encryption Consulting Launches CertSecure Manager MCP Server
Qount Launches MCP Connector for Accounting Data
Lumos Launches MCP Governance for Claude Code and Codex
Daily AI Brief: the AI news that matters, in your inbox.