Information Density: JFrog – Signal Evidence & AI Readability

[IMG: cube]

[IMG: cube]

[IMG: cube]

[IMG: wave]

[IMG: wave]

[H1] Deliver Trusted Software in the AI Era

Break down software delivery silos with one system of record for the software supply chainThe System of Record for the Software Supply Chain

Free Trial

Book a Demo

[H2] Manage, Secure, and Govern Your AI and Software Assets from One Platform

Artifact Management

Supply Chain Security

Agent Lifecycle

App Risk Governance

See the JFrog Platform

[H2] What’s New with JFrog

[H3] Package Traffic Controller

Bring software supply chain security to the network edge. Intercept and redirect direct package requests made by developers, agents, and AI users through JFrog for vetting and logging

Learn More

[H3] The JFrog 2026 Software Supply Chain Security State of the Union

AI has moved from experimentation to a structural force – widening the gap between reported security confidence and the risks actually accumulating in your supply chain.

Read the Report

[H3] JFrog Snippet Detection

Add a new layer of code security that uncovers and governs copy pasted and AI-generated code snippets that traditional scanners don’t alert on.

Learn More

[H3] JFrog MCP Registry

Eliminate gaps in MCP security and governance by ensuring every MCP server passes through the same rigorous, automated policies used for software artifacts.

Learn More

[H3] JFrog Agent Skills Registry

Power autonomous agents with verified and secured agent skills, managed in your trusted source for AI assets. Scale agentic workflows without compromising on security.

Learn More

[H3] 99.99% Premium Availability

JFrog now offers an in-region uptime SLA of 99.99% ensuring software factory resilience for always-on delivery.

Learn More

[H3] JFrog Total Economic Impact™ Report

A commissioned Forrester study shows how organizations cut costs, boost engineering efficiency, and reduce risk with JFrog’s security solutions.

Download Report Now

See All Announcements

[H2] Empowering Everyone Everywhere

[H3] Serving Enterprise Teams Across All Industries

Developers

Leaders

DevOps

Security

AI/MLOps

IoT

[IMG: Quotation Marks]

We want our developers focused on creativity, not administration. Now we’re reducing complexity and unlocking developer happiness – ultimately making them more productive as a result.
Khosro Rahbar, Director IT Application Lifecycle Management, Siemens

[IMG: Quotation Marks]

By deploying JFrog, we’ve seen less vulnerabilities, which has given our developers more time to focus on developing new applications. And with the different development teams all being on the same platform, it has centralized and streamlined the process.
Billy Norwood, CISO, FFF Enterprises

[IMG: Quotation Marks]

Migrating to JFrog’s SaaS platform allowed us to shift our focus from platform maintenance to value-generating initiatives, significantly improving our operational efficiency.
Glenn McDonald, Head of Engineering Services, Iress

[IMG: Quotation Marks]

I follow the basic principles for AppSec -- Prevent, Detect, Remediate. And when I look at the offerings from JFrog, they're checking those boxes for me.
James Carter, Distinguished Engineer, Deloitte

[IMG: Quotation Marks]

Before… delivering a new AI model took weeks... Now the research team can work independently and deliver while keeping the engineering and product teams happy. We had 5 new models running in production within 4 weeks.
Idan Schwartz, Head of Research, Spot (by NetApp)

[IMG: Quotation Marks]

As our business grew, JFrog Connect helped us enhance our operations. Being able to automate and push software updates across multiple devices at once saves us time and resources with each version we deployed. When you consider the cost of an engineer’s time, it was an easy call.
Senior Manager, DevOps, Telehealth

[IMG: wave]

[IMG: wave]

[H2] Serving over 80% of the Fortune 100

[IMG: wave]

Ecosystem Freedom,Not Lock-inEcosystem Freedom,Not Lock-in

To your entire ecosystem: welcome to the era of automated, integrated, extendable, secure software supply chain management.

Learn More

[H2] Ready to Try JFrog?
Get hands-on with a self-guided tour or a free trial,
or contact our team to discuss your needs.

Take A Tour

Start Free Trial

Book A Demo

[IMG: https://speedmedia2.jfrog.com/08612fe1-9391-4cf3-ac1a-6dd49c36b276/media.jfrog.com/wp-content/uploads/2025/09/08125843/ai-catalog-logo.png]

[H1] Trust and Govern Enterprise AI

Establish unified, enterprise-grade delivery, security and governance over your AI supply chain.

Book a Demo

[H3] MCP Governance

Your control plane for MCP servers, enabling managed and governed access to MCP tools. JFrog reduces security risk and ensures agents and developers cannot execute unauthorized or destructive commands via malicious MCP servers.

Learn More

[H3] Agent Skills Registry

Your central hub for managing and securing AI Agent Skills. JFrog ensures every agent skill is vetted for trusted use so developers can build and deploy autonomous agents with total confidence, knowing every capability is secure and compliant.

Learn More

[H2] What is JFrog AI Catalog?

The JFrog AI Catalog is the single system of record for your enterprise AI supply chain. It provides centralized governance and proactive security for all AI workloads, from internal and third party models, to Agent Skills Registry, and MCP servers, enabling you to eliminate Shadow AI and deliver trusted AI applications with speed and control.

Read the Solution Sheet

[IMG: Play]

[H2] Discover all AI assets

Access a centralized registry for all enterprise AI assets, from models to MCP servers, enabling your teams to discover, evaluate, and utilize the right components for rapid development from a single source of truth.

[IMG: ai assets]

[H2] Detect & eliminate Shadow AI

Expose every unmanaged AI model or API call across your enterprise, providing you with a complete view to identify and block ungoverned, non-compliant, or malicious AI usage.

[IMG: Shadow AI]

[H2] Govern every AI workload

Define and automatically enforce security and compliance policies over every AI asset. Proactively block non-compliant, unvetted, or malicious workloads to ensure enterprise-wide trust.

Learn More

[IMG: govern ai workload]

Learn More

[H2] Connect any AI asset

Use a secured AI Gateway for simple one-click deployment of models, fast connection to APIs, and single-line configuration of MCP servers, accelerating the path from discovery to production.

Learn More

[IMG: deploy connect ai asset]

Learn More

AI FreedomDoesn’t Mean Losing Control

JFrog AI Catalog provides simple and secureaccess to the evolving AI ecosystem

Learn More

[H2] Get Started with JFrog Today

Utilize the latest AI Innovations without compromising on governance, security, or trust. Only with the JFrog AI Catalog.

Book a Demo

Blog Home

Software supply chains are the #1 attack vector for cybercriminals, and the challenge isn’t just finding vulnerabilities; it’s fixing them fast while ensuring security, compliance, and developer productivity. As supply chains grow in complexity, traditional tools aren’t enough; organizations need intelligent, autonomous assistance embedded directly into developer workflows.
We are pleased to announce that JFrog is introducing Agentic Software Supply Chain Security to help organizations reduce risk, cut costs, and accelerate delivery. By combining JFrog’s trusted platform with AI-driven automation, development teams can shift from reactive security practices to proactive, agentic software supply chain security, curating safer software packages, remediating CVEs, and coding with confidence.
[H2] Agentic Software Supply Chain Security from JFrog
Agentic Software Supply Chain Security is a culmination of various tools and capabilities within the JFrog Software Supply Chain Platform as well as integrations with external partners, and includes JFrog Catalog, Curation, SAST, GitHub Copilot, and VSCode. Here’s how they all work together to shift development teams from reactive security practices to proactive, agentic security.
[H3] Curation: Faster and Smarter Package Selection
Open source is the foundation of modern software, but with millions of packages and varying license obligations, curating safe and compliant dependencies can be daunting.
With JFrog Catalog & Curation, developers can now build with confidence. AI-powered agents, connected to JFrog security solutions via the JFrog remote MCP (Model Context Protocol), analyze package metadata, security posture, and compliance with organizational policies, helping teams select the best open-source libraries at speed. By ensuring developers can only use the safest, policy-compliant packages, teams avoid failed builds from vulnerabilities and keep CI/CD pipelines running smoothly, shortening release cycles and accelerating delivery.
[H4] Curation Workflow Example:
Step 1: A developer writes code with the assistance of an AI agent (e.g., GitHub Copilot).
Step 2: Copilot selects the required packages and validates with Curation through JFrog MCP.
Step 3: JFrog Curation evaluates the package against security and license policies and CVE databases supported by JFrog Catalog
Step 4: The AI Agent with JFrog insights (via remote MCP) replaces bad package versions with ones that pass the Curation policy.
The result: faster innovation without sacrificing security or governance.
[H3] Secure and Friendly Agentic Source Code Remediation
Security shouldn’t slow developers down. Instead, it should meet them in the IDE, during coding, in a way that promotes frictionless innovation.
JFrog SAST surfaces source code vulnerabilities directly in the IDE. With agentic remediation, developers get contextual, friendly, and actionable AI-suggested code changes in real-time so that they don’t have to sift through security logs or reports. The JFrog local SAST MCP connects the JFrog Platform to your chosen AI agent. The agent gets insights from the SAST engine, which scans the codebase and generates SAST findings.
[H4] Coding Workflow Example:
Step 1: A developer writes new code.
Step 2: JFrog scans the code and flags any vulnerable patterns, e.g., SQL injection
Step 3: The developer asks the AI agent to fix any SAST issues in the code.
Step 4: The AI Agent receives remediation information from the SAST engine to provide a secure code fix inline (“Convert to parameterized query”).
Step 5: The developer reviews and accepts or rejects the suggested code.
This ensures teams aren’t just finding problems, but are continuously writing secure code by default.
[H3] Automated Remediation or “Ask Copilot to Fix”
Vulnerabilities in open-source dependencies (CVEs) remain one of the most exploited attack vectors in the software supply chain. Identifying them is only half the battle; the real challenge is remediating them quickly and accurately.
The “Ask Copilot to Fix” feature is part of our VSCode extension and automatically suggests or applies patches, dependency upgrades, or safe alternatives. The “Ask Copilot to Fix” action can be triggered for various security findings, including those from SAST, Secrets Scanning, and IaC analysis. This makes remediation seamless, efficient, and integrated directly into the developer experience.
[H4] CVE Remediation Workflow Example:
The  VSCode extension scans your entire codebase.
If you have JFrog Advanced Security, the scan includes contextual analysis, SAST, secrets detection, and Infrastructure as Code (IaC) analysis.
For example, the scan detects a CVE in a dependency, log4j version 2.14.1.
The developer then chooses the option to ‘ask Copilot to fix’ the detected issue.
The remediation information is passed to Copilot from JFrog.
Copilot generates the code fix based on the JFrog remediation information.
Instead of overwhelming teams with alerts, JFrog empowers them with autonomous, agentic remediation that keeps the supply chain secure without slowing delivery.
[H2] The JFrog Advantage
JFrog helps teams shift from reactive to proactive agentic security. With JFrog’s deep security research at its core, the JFrog platform ensures comprehensive protection and actionable intelligence. By connecting AI agents to the JFrog platform via MCP servers, and by using the JFrog VSCode plugin, developers gain:
Automated package curation to reduce supply chain risk.
Inline, context-aware code security and remediation.
Seamless CVE and other fixes that accelerate release cycles.
This isn’t just an AI assistant; it’s agentic, autonomous remediation that transforms DevSecOps into a self-healing software supply chain. Unlike point solutions, JFrog delivers:
End-to-end visibility from code to runtime.
Agentic AI workflows embedded across curation, coding, and CVE remediation.
Trusted security intelligence integrated with GitHub, IDEs, and enterprise DevSecOps pipelines.
With JFrog, organizations can move from reactive patching to proactive, autonomous, and continuous security.
[H3] Business Outcomes
Here are the outcomes organizations can expect with Agentic Software Supply Chain Security from JFrog.
[H4] Speed to Market
AI-curated open-source packages reduce delays in sourcing and compliance checks.
Developers spend less time researching libraries and more time innovating.
This can yield faster coding and remediation of CVEs.
[H4] Risk Reduction
Automated CVE remediation can help shrink exposure windows
Agentic source code remediation reduces human error and ensures security by design.
Improved license compliance reduces legal and reputational risk.
A significant ROI can be achieved through avoided breaches; the average cost of a software supply chain incident exceeds $4.4M.
[H4] Operational Efficiency
AI-powered remediation reduces manual triage, freeing security engineers for high-value tasks.
Seamless IDE integration lowers developer context-switching, improving productivity.
Automated remediation realizes a significant reduction in time spent evaluating open-source dependencies.
[H4] Cost Savings
Faster cycles mean fewer incidents, outages, and lower breach-related costs.
With AI-powered code generation and remediation assistance, developers can realize up to a 2x productivity boost as AI handles repetitive tasks.
[H2] The Future of Agentic Security
The future of DevSecOps isn’t just about shifting left, it’s about agentic AI: autonomous security that works as fast as your developers.
With agentic AI capabilities embedded across the JFrog Platform, developers gain:
Speed through AI-curated open-source packages.
Security with SAST-driven agentic code remediation.
Seamlessness in CVE detection and auto-fixes.
Confidence to deliver software at scale, without compromise.
By combining trusted DevSecOps foundations with autonomous AI agents, JFrog is making Agentic Software Supply Chain Security a reality, helping organizations deliver secure, reliable, and compliant software at the pace of innovation. To learn more, schedule a demo, take an online tour, or head over to the GitHub Marketplace to connect your GitHub and JFrog instances to enjoy AI-assisted, secure coding.

Sign up for blog updates

[H3] Popular Tags

CI/CD

Artifactory

Best Practices

DevOps

Xray

[H2] New insights from +1,400 security & DevOps leaders. Get the Full Report.

Download Now

[H2] Thank You!

[H1] Govern and Control MCP at Enterprise Scale

A centralized MCP Registry that ensures developers and agents only use pre-vetted MCP servers with fine-grained access control at the MCP tool level.

Book a Demo

[H2] What is JFrog MCP Registry?

The JFrog MCP Registry is an enterprise-grade control plane that serves as the single source of truth for all your MCP servers, enabling AI Agents and developers to access MCP tools in a managed and governed way. With the JFrog MCP Registry, you can reduce security risk and ensure AI agents and developers cannot execute unauthorized or destructive commands using malicious MCP servers.

Learn More

[H2] Ungoverned MCPs Are Exploitable

Unsecured MCP servers expose your agentic workflows to critical security risks.

[H3] Over-Privileged AI Agent Access

Lack of granular control over MCP tools permissions allows AI agents to access sensitive internal data without restrictions. This leads to destructive operations being executed in your production environment.

[H3] Unvetted MCP Servers

Developers are using unverified MCP servers from public sources directly on their machines. This exposes your organization to supply chain attacks. Compromised tools running on localhost effectively bypass your perimeter security.

[H3] Fragmented AI Management

Without a single system of record, you are flying blind. Managing scattered permissions and local configurations across developers at enterprise scale is unmanageable and creates massive exposure, making it impossible to audit every active MCP connection.

[H2] The First Enterprise-Grade MCP Registry

The unified control plane to secure, manage, and scale your agentic software supply chain

[H3] MCP Governance at Scale

Transform the “wild west” of MCPs into a fully governed ecosystem. Control MCP servers and their tools usage with granular role-based permissions across the supply chain.

[H3] Block Unauthorized Servers

Don’t just scan – block. The only registry that proactively halts malicious and unverified MCP servers at the gate based on your security policies, neutralizing threats before they ever breach your organization.

[H3] Unified AI Registry

Stop managing AI in silos. MCP Registry is part of JFrog AI Catalog, the control plane built for all AI artifacts, unifying your custom and third-party MCP servers, agent skills, models and binaries into a single, trusted system of record.

[H2] NEW JFrog Agent Skills Registry for NVIDIA OpenShell

Learn More

[IMG: mcp banner bg]

Learn More

[H2] Granular Access Control

Granular tool permissions restrict MCP usage to authorized teams and projects, preventing AI agents from accessing or modifying sensitive data beyond their scope.

[IMG: mcp asset 4]

[H2] Automated Policy Engine

The MCP Registry enforces governance policies based on license type, vulnerability severity, or operational risk at the point of request, proactively blocking unverified servers to neutralize supply chain risks before execution.

[IMG: mcp asset 3]

[H2] Secure MCP Guard

The lightweight CLI Guard routes local IDE connections through a secure bridge, authenticating every request to ensure AI models only interact with approved, verified MCP servers.

[IMG: mcp asset 1]

[H2] Integrated with Coding Agents

The JFrog MCP Registry integrates with coding agents, like Cursor and Claude Code, to enforce secure connectivity through a centralized MCP Guard, ensuring only pre-vetted MCP servers are accessible.

[IMG: mcp visual 7]

[H2] How it works: The Governed Agentic Software Supply Chain

The JFrog MCP Registry provides a unified control plane that treats MCP servers as standard software artifacts, applying centralized, multi-layered governance across the entire agentic supply chain.
Perimeter Defense: Integrates with JFrog Curation to proactively block malicious or unverified servers before they reach your environment.
Local Control: Uses a Secure MCP Guard as a local proxy to authenticate tool calls and enforce granular RBAC, preventing unauthorized data access by coding agents like Cursor or Claude Code.
Platform Policy: As part of the JFrog AI Catalog, it integrates natively with JFrog Artifactory for storage and JFrog Curation for policy setting, allowing you to manage AI models, agent skills, and MCP tools alongside your software dependencies on a single, unified platform.

[IMG: mcp diagram]

[H2] Additional Resources on Trusted AI Adoption

Solution Sheet

[H3] Trusted AI Adoption With the JFrog AI Catalog

Learn More

Whitepaper

[H3] The Tech Leader’s Guide to AI & MLOps

Learn More

eBook

[H3] Taming the Agentic Supply Chain

Learn More

Blog

[H3] The MCP Trojan Horse: AI’s Hidden
Security Risk

Learn More

[H2] Frequently Asked Questions

What is an MCP Registry?

An MCP Registry is a centralized governance control plane that serves as the single source of truth for all types of Model Context Protocol (MCP) servers. It acts as a secure “supply chain firewall,” ensuring that developers and AI agents only access approved and MCP servers rather than unverified public ones.

Why do enterprises need an MCP Registry?

Enterprises need a registry to eliminate uncontrolled MCP usage and gain visibility into which AI agents are connecting to internal systems, and what capabilities and permissions they are allowed to use. It automates the configuration of MCP connections across hundreds of developer environments and prevents data exfiltration by blocking unverified servers at the point of request.

How does an MCP Registry prevent potential threats?

The registry neutralizes threats by preventing unvetted MCP servers from gaining operational access to internal systems. By governing the “hands” of the AI (the MCP server), it prevents agents from accessing or modifying sensitive data beyond their authorized scope.

What are MCP server security risks?

Because MCP servers give AI models the ability to execute code autonomously, unmanaged servers can grant unauthorized system access or leak sensitive data. Without a registry, developers expose the organization to supply chain attacks by connecting directly to public, potentially malicious repositories.

How does JFrog block malicious MCP servers?

JFrog enforces “Shift-Left” blocking at the source. The Curation-based automated policy engine validates every request against security policies (e.g., CVE scores, license types) and physically blocks the acquisition of malicious artifacts before they ever reach the developer’s machine.

How does MCP governance work?

Governance is enforced via the Local MCP Guard, a lightweight proxy that transparently handles authentication and project-based permission checks directly on the developer’s machine. This ensures that coding agents only connect to approved MCP servers explicitly authorized for the user’s specific project, preventing direct public connections and enforcing zero-trust access.

How is JFrog different from public MCP registries?

Unlike public registries that serve as simple lists of links, JFrog is a platform built on three unique differentiators. We manage MCP servers as immutable binary artifacts (preventing changes), we block malicious tools at the gate before download, and we provide a unified system of record that governs your AI tools alongside your existing software supply chain.

Which coding agents and IDEs are supported?

The Registry is compatible with MCP-compliant coding agents and IDEs, such as Cursor, Claude Code, and VS Code. Developers connect via a secure MCP Guard that routes traffic to vetted internal servers, ensuring seamless integration without exposing the network to the public internet.

Is the MCP Registry included in the JFrog Platform?

Yes, it is a core feature of the JFrog AI Catalog. It integrates natively with JFrog Artifactory for storage and JFrog Curation for policy setting, allowing you to manage AI models, agent skills, and MCP tools alongside your software dependencies on a single, unified platform.

[H2] Turn MCP Risk Into a Trusted Supply Chain

Book a Demo