JFrog Ltd. announced the launch of a new plug-in for AI Coding Agents in Claude Code. The company developed the plugin in partnership with Anthropic. Now, with JFrog’s trusted platform, users of the Claude Code can run governed and supply-chain aware AI Coding Agents.
The new integration enhances security for AI Coding Agents in enterprise software development environments. It further expands the JFrog Software Supply Chain Platform into one of the fastest-growing AI coding ecosystems in the industry.
JFrog is a trusted system of record for software artifacts, binaries and AI assets As a result, the company is dedicated to delivering improved governance, compliance and transparency throughout AI-powered development workflows.
The announcement comes as businesses are taking more and more advantage of AI-powered development tools. But organizations are also dealing with increasing challenges around security, compliance and software supply chain risks.
Anthropic has recently emphasized the need for increased safeguards of AI agents. Capabilities of evolving agents continue to broaden potential attack surfaces. Therefore, organizations need to spend more on agent-specific security frameworks and standards.
“AI-enabled innovation can’t be at the expense of security or compliance. Companies need a system of record with visibility into the decisions these agents make – that’s what our integration with Anthropic’s Claude Code provides.” – Yoav Landman, JFrog CTO
According to JFrog, many AI agents currently make decisions without software supply chain context. As a result, organizations face greater exposure to malicious packages, vulnerabilities, and unmanaged AI assets.
“AI agents are active participants in the software supply chain, making decisions about dependencies, builds, and deployments – but most of them are doing it blind, without any supply chain context. This is often how malicious packages, vulnerabilities, and ungoverned AI assets enter production today, exposing organizations to software supply chain attacks,” said Yoav Landman, Co-Founder and CTO of JFrog. “AI-enabled innovation cannot come at the expense of security or compliance. Enterprises need a universal system of record with real-time control and visibility into the decisions these agents make, that’s what this integration enables.”
Supporting Agentic DevSecOps and Software Supply Chain Security
AI coding tools continue generating massive numbers of software binaries. Currently, the JFrog Platform manages more than 18 billion artifacts. That figure represents a 136 percent increase from the previous year.
To address this growth, the new Claude Code plugin provides developers with governed access to artifacts and dependencies. In addition, organizations can scan, curate, and secure assets consumed by AI agents.
The plugin also introduces specialized JFrog Platform Skills. These capabilities allow developers and agents to execute platform operations through natural language commands.
Combined with the JFrog MCP Registry and JFrog Agent Skills Registry, the plugin delivers several key benefits.
Companies gain real-time governance through combined package security, license compliance and validation. Also agents can enforce policies during development workflows.
The solution also strengthens MCP and agent skills governance. Therefore, developers and AI users access only verified and secure MCP servers and agent skills.
The platform accelerates DevOps workflows. AI agents can handle repository management, project provisioning, and routine platform operations. As a result, developers spend more time building applications.
The plugin also improves auditability. Security teams gain end-to-end traceability from source code commits to final build artifacts. Consequently, organizations can respond to incidents faster and demonstrate compliance more efficiently.
JFrog Supports Multi-Agent Environments
JFrog believes organizations will continue adopting multiple AI agents. Therefore, the company focuses on supporting agent choice while maintaining governance controls.
The JFrog Platform provides three core layers of connectivity across AI coding environments.
JFrog Platform Skills deliver deep operational knowledge across the platform. These skills support vulnerability scanning, curation checks, and provenance verification through natural language.
JFrog MCP Tools provide standardized access to compliance, security, and artifact data. Consequently, organizations maintain consistent governance across different AI agents.
JFrog offers agent-native plugin support. Claude Code joins Cursor and VS Code Copilot as supported environments. Therefore, users can access JFrog capabilities directly within their preferred development tools.
Together, these capabilities position the JFrog Platform as a foundational system of record for multi-agent environments. Also governance, security, and provenance remain consistent regardless of the AI tool in use.
For related updates on digital trust and cybersecurity, explore our SOC News.
Source: Businesswire
