JFrog
Model Context Protocol (MCP) Server for the JFrog Platform API, enabling repository management, build tracking, release lifecycle management, and more.
What is JFrog?
JFrog is a Model Context Protocol (MCP) server that allows AI assistants like Claude, Cursor, and VS Code to model context protocol (mcp) server for the jfrog platform api, enabling repository management, build tracking, release lifecycle management, and more.
Model Context Protocol (MCP) Server for the JFrog Platform API, enabling repository management, build tracking, release lifecycle management, and more.
This server falls under the Cloud Services category on MCPgee, the world's largest MCP server directory with 33,000+ servers.
Features
- Model Context Protocol (MCP) Server for the JFrog Platform A
Use Cases
Maintainer
Works with
Installation
Manual Installation
npx mcp-jfrogConfiguration
Configuration Details
claude_desktop_config.json
Performance
Response Metrics
Resource Usage
How to Set Up and Use JFrog
The JFrog MCP Server connects AI assistants to the JFrog Platform API, enabling natural-language management of Artifactory repositories, build tracking, release lifecycle operations, runtime cluster inspection, and security vulnerability analysis via JFrog Xray. With 22 available tools covering repository creation, AQL artifact queries, package curation status, and CVE lookups, DevSecOps engineers and platform teams can interrogate and manage their software supply chain without leaving their AI coding environment.
Prerequisites
- Node.js 18 or later installed
- A JFrog Platform instance (cloud or self-hosted) with an access token
- JFROG_URL: the base URL of your JFrog instance (e.g., https://yourcompany.jfrog.io)
- JFROG_ACCESS_TOKEN: a JFrog access or identity token with appropriate permissions
- An MCP-compatible client such as Claude Desktop or Claude Code
Clone the mcp-jfrog repository
Clone the official JFrog MCP server repository to your local machine.
git clone https://github.com/jfrog/mcp-jfrog.git
cd mcp-jfrogInstall dependencies and build
Install npm dependencies and compile the TypeScript source.
npm install
npm run buildSet required environment variables
Both JFROG_URL and JFROG_ACCESS_TOKEN are required. Generate a token in the JFrog UI under Administration > Identity and Access > Access Tokens.
export JFROG_URL=https://yourcompany.jfrog.io
export JFROG_ACCESS_TOKEN=your-access-token-hereAdd the server to your MCP client configuration
Edit claude_desktop_config.json to register the JFrog MCP server with the required credentials passed as environment variables.
Restart your MCP client and verify
Restart Claude Desktop or Claude Code. Ask the AI to check JFrog availability to confirm the connection is working.
JFrog Examples
Client configuration
Claude Desktop config for the JFrog MCP server using the built binary.
{
"mcpServers": {
"jfrog": {
"command": "node",
"args": ["/path/to/mcp-jfrog/dist/index.js"],
"env": {
"JFROG_URL": "https://yourcompany.jfrog.io",
"JFROG_ACCESS_TOKEN": "your-access-token-here"
}
}
}
}Prompts to try
These prompts exercise the 22 tools across repository management, build tracking, security, and runtime inspection.
- "Is my JFrog instance available and responding?"
- "List all repositories in my Artifactory instance"
- "Create a new local Maven repository called my-libs-release"
- "List all builds in JFrog"
- "Search for all artifacts in the libs-release repo using AQL"
- "Get vulnerability information for package lodash version 4.17.20"
- "What is the curation status of the npm package express 4.18.2?"
- "List all running images in my JFrog runtime clusters"Troubleshooting JFrog
Authentication errors (401 Unauthorized)
Verify JFROG_ACCESS_TOKEN is a valid access token (not an API key). Generate a new one in the JFrog UI under Administration > Identity and Access > Access Tokens with the required scopes for your operations.
JFROG_URL format causing connection failures
The URL should not have a trailing slash and should point to the platform root, e.g., https://yourcompany.jfrog.io — not to a specific repository or API path.
Xray vulnerability tools return empty results
JFrog Xray must be enabled and configured on your instance. Confirm that the artifacts you are querying have been indexed by Xray, which can be set up under the Xray > Indexed Resources settings.
Frequently Asked Questions about JFrog
What is JFrog?
JFrog is a Model Context Protocol (MCP) server that model context protocol (mcp) server for the jfrog platform api, enabling repository management, build tracking, release lifecycle management, and more. It connects AI assistants to external tools and data sources through a standardized interface.
How do I install JFrog?
Follow the installation instructions on the JFrog GitHub repository. Clone the repo, install dependencies, and add the server config to your AI client.
Which AI clients work with JFrog?
JFrog works with all major MCP-compatible AI clients including Claude Desktop, Claude Code, Cursor, VS Code (GitHub Copilot), Windsurf, and Cline.
Is JFrog free to use?
Yes, JFrog is open source and available under the Apache-2.0 license. You can use it freely in both personal and commercial projects.
JFrog Alternatives — Similar Cloud Services Servers
Looking for alternatives to JFrog? Here are other popular cloud services servers you can use with Claude, Cursor, and VS Code.
Open WebUI
★ 138.2kUser-friendly AI Interface (Supports Ollama, OpenAI API, ...)
Anything LLM
★ 60.4kThe all-in-one AI productivity accelerator. On device and privacy first with no annoying setup or configuration.
LocalAI
★ 46.4kLocalAI is the open-source AI engine. Run any model - LLMs, vision, voice, image, video - on any hardware. No GPU required.
Nacos
★ 33.0kan easy-to-use dynamic service discovery, configuration and service management platform for building AI cloud native applications.
Xiaozhi ESP32
★ 26.7k本项目为xiaozhi-esp32提供后端服务，帮助您快速搭建ESP32设备控制服务器。Backend service for xiaozhi-esp32, helps you quickly build an ESP32 device control server.
Gateway
★ 11.8kA blazing fast AI Gateway with integrated guardrails. Route to 1,600+ LLMs, 50+ AI Guardrails with 1 fast & friendly API.
Browse More Cloud Services MCP Servers
Explore all cloud services servers available in the MCPgee directory. Each server includes setup guides for Claude, Cursor, and VS Code.
Set Up JFrog in Your Editor
Choose your AI client for step-by-step setup instructions.
Quick Config Preview
Add this to your claude_desktop_config.json or .cursor/mcp.json
Ready to use JFrog?
Browse our complete directory of 33,000+ MCP servers, read setup guides for your editor, and start building with the Model Context Protocol.