TLDR: JFrog has launched its new Model Context Protocol (MCP) Server, an architecture designed to enable Large Language Models (LLMs) and AI agents to securely interact with the JFrog Platform. This innovation aims to significantly boost developer productivity, streamline software development workflows, and integrate AI capabilities directly into coding environments using natural language commands.
Sunnyvale, California – July 17, 2025 – JFrog Ltd. (NASDAQ: FROG), a leading provider of software supply chain solutions, today announced the introduction of its new Model Context Protocol (MCP) Server. This groundbreaking architecture is set to revolutionize software development by securely connecting Large Language Models (LLMs) and AI agents directly with the JFrog Platform, including popular agentic coding development environments and Integrated Development Environments (IDEs).
The MCP Server is built on the Model Context Protocol, an open, industry-standard integration framework specifically designed to link AI systems with external tools, data, and services. This allows developers to leverage natural language commands, such as ‘Create a new local repository’ or ‘Do we have this package in our organization?’, to interact seamlessly with the JFrog Platform from within their preferred development environments, eliminating the need for constant context switching.
Yoav Landman, Co-Founder and CTO of JFrog, emphasized the significance of this launch, stating, “The developer tool stack and product architecture has fundamentally changed in the AI era. With the launch of the JFrog MCP Server, we’re expanding the open integration capabilities of the JFrog Platform to seamlessly connect with LLMs and agentic tools. This allows developers to natively integrate their MCP-enabled AI tools and coding agents with our Platform, enabling self-service AI across the entire development lifecycle, which helps increase productivity and build smarter, more secure applications faster.”
The benefits of the MCP Server extend beyond simple command execution. Teams will gain immediate awareness of open-source vulnerabilities and software package usage, enhancing security and compliance. AI automation also simplifies complex queries that previously required advanced developer knowledge, enabling all teams to work smarter and faster. This integration is poised to significantly increase developer productivity and streamline workflows across the entire software development lifecycle.
Security has been a paramount consideration in the development of the MCP Server. JFrog’s implementation relies on robust HTTPS connections and OAuth 2.1 authentication, ensuring modern, token-based security. This approach enforces scoped access per tenant and tool, guaranteeing that only authorized users and systems can interact with the platform. The company also highlighted that its Security Research Team recently discovered vulnerabilities, such as CVE-2025-6514, which could potentially hijack MCP clients and execute remote code, underscoring the critical importance of secure implementation and JFrog’s commitment to addressing such risks.
The JFrog MCP Server is available to JFrog SaaS customers and supports multi-tenant environments across major cloud platforms. It is implemented as a remote, secure, cloud-native server, providing automatic version updates and improvements with minimal maintenance. Developers can currently test and provide feedback on the new feature during a preview period, with more information available via the AWS marketplace and JFrog’s step-by-step implementation guides.
Also Read:
- Sonatype Expands Reach with Full Product Suite Now Available in AWS Marketplace AI Agents and Tools Category
- Honeycomb Launches Hosted Model Context Protocol (MCP) Server on AWS Marketplace, Enhancing AI Agent Observability
This strategic move solidifies JFrog’s position at the forefront of AI-driven DevSecOps innovation, addressing the growing demand for seamless, secure, and scalable AI integration across all development workflows, ultimately empowering customers to build applications smarter, faster, and more securely at scale.
