JFrog MCP Server
Experimental Model Context Protocol server that enables access to JFrog Platform API capabilities including repository management, build tracking, artifact searching, and package security analysis.
What is JFrog MCP Server?
JFrog MCP Server is a Model Context Protocol (MCP) server that allows AI assistants like Claude, Cursor, and VS Code to experimental model context protocol server that enables access to jfrog platform api capabilities including repository management, build tracking, artifact searching, and package security analysis.
Experimental Model Context Protocol server that enables access to JFrog Platform API capabilities including repository management, build tracking, artifact searching, and package security analysis.
This server falls under the Cloud Services category on MCPgee, the world's largest MCP server directory with 33,000+ servers.
Features
- Experimental Model Context Protocol server that enables acce
Use Cases
Maintainer
Works with
Installation
Manual Installation
npx jfrog-mcp-serverConfiguration
Configuration Details
claude_desktop_config.json
Performance
Response Metrics
Resource Usage
How to Set Up and Use JFrog MCP Server
The JFrog MCP Server is an experimental Model Context Protocol server that exposes 22 tools covering the JFrog Platform API, including repository management, build tracking, runtime container monitoring, AQL artifact queries, package vulnerability analysis, and curation status checks. It allows AI assistants to query and manage your JFrog Artifactory instance in natural language, making it easier to investigate security issues, search artifacts, and monitor CI/CD pipelines without leaving your AI client.
Prerequisites
- A JFrog Platform instance (Artifactory cloud or self-hosted) with a valid URL (e.g. https://yourcompany.jfrog.io)
- A JFrog Access Token or Identity Token with appropriate permissions for the operations you want to perform
- Node.js 18 or later and npm (for building from source), or Docker
- An MCP-compatible AI client (Claude Desktop, Cursor, or similar)
Install via Smithery (automated, recommended)
Smithery handles the build and client registration in one step for Claude Desktop.
npx -y @smithery/cli install @jfrog/mcp-jfrog --client claudeBuild from source manually
Clone the repository and build the TypeScript project. The compiled server will be in the dist directory.
git clone https://github.com/jfrog/mcp-jfrog.git
cd mcp-jfrog
npm install
npm run buildBuild a Docker image (alternative)
If you prefer Docker, build the image locally for use in your MCP config.
docker build -t mcp/jfrog -f Dockerfile .Set required environment variables
The server requires two environment variables. JFROG_ACCESS_TOKEN is a token from your JFrog Platform (Identity Administration > Access Tokens). JFROG_URL is your platform base URL.
export JFROG_ACCESS_TOKEN="your-jfrog-access-token"
export JFROG_URL="https://yourcompany.jfrog.io"Add to Claude Desktop config (Docker variant)
Use Docker to run the server so environment variables stay out of your config file.
{
"mcpServers": {
"jfrog": {
"command": "docker",
"args": [
"run", "--rm", "-i",
"-e", "JFROG_ACCESS_TOKEN",
"-e", "JFROG_URL",
"mcp/jfrog"
],
"env": {
"JFROG_ACCESS_TOKEN": "your-token-here",
"JFROG_URL": "https://yourcompany.jfrog.io"
}
}
}
}Add to Claude Desktop config (Node.js variant)
If running from the compiled source, reference the built JavaScript file directly.
{
"mcpServers": {
"jfrog": {
"command": "node",
"args": ["/path/to/mcp-jfrog/dist/index.js"],
"env": {
"JFROG_ACCESS_TOKEN": "your-token-here",
"JFROG_URL": "https://yourcompany.jfrog.io"
}
}
}
}JFrog MCP Server Examples
Client configuration
Docker-based MCP config for Claude Desktop connecting to a JFrog Cloud instance.
{
"mcpServers": {
"jfrog": {
"command": "docker",
"args": [
"run", "--rm", "-i",
"-e", "JFROG_ACCESS_TOKEN",
"-e", "JFROG_URL",
"mcp/jfrog"
],
"env": {
"JFROG_ACCESS_TOKEN": "eyJ...",
"JFROG_URL": "https://acme.jfrog.io"
}
}
}
}Prompts to try
Query your JFrog Platform using natural language. The server maps requests to one of 22 available tools.
- "List all local repositories in my Artifactory instance"
- "Find all artifacts in the libs-release repo that contain 'log4j' in their name"
- "Show me the vulnerability summary for com.example:my-app:1.0.0"
- "What Docker images are currently running in the JFrog Runtime cluster?"
- "Run an AQL query to find all artifacts modified in the last 7 days"Troubleshooting JFrog MCP Server
401 Unauthorized errors when calling tools
Verify JFROG_ACCESS_TOKEN is a valid, unexpired token with sufficient permissions. In the JFrog Platform, go to Administration > Identity and Access > Access Tokens to create a new token with the required scopes.
Docker command not found or image not built
Ensure Docker Desktop is running before launching the MCP client. If the image does not exist, run: docker build -t mcp/jfrog -f /path/to/mcp-jfrog/Dockerfile /path/to/mcp-jfrog
Tools appear in the client but always return empty results
Confirm JFROG_URL is your platform base URL without a trailing slash (e.g. https://acme.jfrog.io, not https://acme.jfrog.io/). Also verify that your token has read permissions on the repositories or resources you are querying.
Frequently Asked Questions about JFrog MCP Server
What is JFrog MCP Server?
JFrog MCP Server is a Model Context Protocol (MCP) server that experimental model context protocol server that enables access to jfrog platform api capabilities including repository management, build tracking, artifact searching, and package security analysis. It connects AI assistants to external tools and data sources through a standardized interface.
How do I install JFrog MCP Server?
Follow the installation instructions on the JFrog MCP Server GitHub repository. Clone the repo, install dependencies, and add the server config to your AI client.
Which AI clients work with JFrog MCP Server?
JFrog MCP Server works with all major MCP-compatible AI clients including Claude Desktop, Claude Code, Cursor, VS Code (GitHub Copilot), Windsurf, and Cline.
Is JFrog MCP Server free to use?
Yes, JFrog MCP Server is open source and available under the Apache 2.0 license. You can use it freely in both personal and commercial projects.
JFrog MCP Server Alternatives — Similar Cloud Services Servers
Looking for alternatives to JFrog MCP Server? 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 MCP Server 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 MCP Server?
Browse our complete directory of 33,000+ MCP servers, read setup guides for your editor, and start building with the Model Context Protocol.