JFrog launches MCP Server to connect AI agents with developer tools

Software supply chain company JFrog Ltd. today introduced a new Model Context Protocol server designed to securely connect large language models and artificial intelligence agents to its Software Supply Chain Platform directly from developers’ integrated development environments.

MCP is an open, industry-standard integration framework designed to connect AI systems with external tools, data and services. JFrog’s new MCP Server allows developers to use natural language commands like “Create a new local repository” or “Do we have this package in our organization?” to interact with the JFrog Platform directly from their IDE or AI assistant.

The new server offers teams immediate awareness of open-source vulnerabilities and package usage either inside or outside their organization without context switching. AI-powered automation also helps simplify complex queries that previously required advanced developer knowledge, helping all teams develop smarter, faster and at scale in less time.

JFrog’s MCP Server is a centralized, cloud-native solution that simplifies and secures AI integration within the software development lifecycle. Available to JFrog software-as-a-service customers, the server supports multitenant environments across major cloud platforms.

Security is a key focus of the server and is built into its foundation with support for OAuth 2.1, enabling modern, token-based authentication. The approach enforces scoped access per tenant and tool, ensuring that only authorized users and systems can interact with the platform.

Notably, the MCP Server offers automatic updates and reduced maintenance overhead by running the same codebase as the local JFrog Platform to ensure that users always have access to the latest features and security enhancements.

The MCP Server also equips developers with essential tools for managing and understanding their software supply chain. Users can create and oversee projects and repositories, monitor build status and perform advanced queries on packages and vulnerabilities without leaving their development environment. Integrated, production-grade monitoring additionally delivers detailed logs and event tracking, providing insights into how tools and workflows are being used.

“Until recently, connecting AI agents to diverse enterprise systems created development bottlenecks, with each integration requiring custom code and ongoing maintenance, which was costly and time-consuming for internal teams to manage,” said co-founder and Chief Executive Yoav Landman. “JFrog’s MCP Server helps solidify our position at the forefront of AI-driven DevSecOps innovation by addressing the growing demand for seamless, secure and scalable use of AI across all development workflows. Customers can now build applications smarter, faster and more securely at scale.”

Image: SiliconANGLE/Reve