JFrog MCP Server Integration

What does “JFrog” MCP Server do?

The JFrog MCP (Model Context Protocol) Server serves as an integration layer between AI assistants and the JFrog Platform API, empowering developers to automate and enhance their DevOps workflows. By leveraging this MCP server, AI clients can perform a variety of operations such as repository management, build tracking, runtime monitoring, artifact search, catalog and curation, and vulnerability analysis. The server acts as a bridge, enabling AI agents to execute tasks like creating and managing repositories, retrieving build information, monitoring runtime clusters, and accessing vulnerability scan summaries. This integration streamlines development and release processes, making it easier for teams to manage their software artifacts and infrastructure efficiently through conversational or programmatic AI interfaces.

List of Prompts

No prompt templates were found in the repository content provided.

List of Resources

No explicit MCP resources were mentioned in the repository content provided.

List of Tools

• check_jfrog_availability
  • Checks if the JFrog platform is ready and functioning. Returns the platform readiness status.
• create_local_repository
  • Creates a new local repository in Artifactory. Accepts parameters such as key, rclass (“local”), packageType, and optional description, projectKey, and environments.
• create_remote_repository
  • Creates a new remote repository to proxy external package registries. Requires key, rclass (“remote”), packageType, url, and optional credentials and configurations.
• create_virtual_repository
  • Aggregates multiple repositories into a single virtual repository. Requires key, rclass (“virtual”), packageType, repositories (list), and optional metadata.
• list_repositories
  • Lists all repositories in Artifactory, with optional filtering by type, packageType, or project.

Use Cases of this MCP Server

• Repository Management
  • Automate the creation and management of local, remote, and virtual repositories, improving efficiency and reducing manual errors in artifact storage operations.
• Build Tracking
  • Easily list and retrieve build information, helping teams monitor build status and history for CI/CD processes.
• Runtime Monitoring
  • View runtime clusters and running container images, aiding in the real-time monitoring and management of infrastructure components.
• Artifact Search
  • Execute advanced AQL queries to search for artifacts and builds, enabling precise and rapid access to required binaries and metadata.
• Vulnerability and Curation Insights
  • Access package information, versions, and vulnerability summaries, helping teams ensure security and compliance throughout the software lifecycle.

How to set it up

Windsurf

1. Ensure you have Node.js installed and access to your MCP server.
2. Open your Windsurf configuration file (usually windsurf.config.json).
3. Add the JFrog MCP Server to the mcpServers object:

{
  "mcpServers": {
    "jfrog": {
      "command": "npx",
      "args": ["@jfrog/mcp-jfrog@latest"]
    }
  }
}

4. Save the configuration file and restart Windsurf.
5. Verify setup by checking the MCP server status in the Windsurf dashboard.

Claude

1. Make sure Claude is installed and accessible.
2. Locate the Claude agent configuration file.
3. Add the JFrog MCP Server using the following JSON snippet:

{
  "mcpServers": {
    "jfrog": {
      "command": "npx",
      "args": ["@jfrog/mcp-jfrog@latest"]
    }
  }
}

4. Save your changes and restart Claude.
5. Confirm the server connection in the Claude UI.

Cursor

1. Install Node.js and ensure Cursor is set up.
2. Open the Cursor configuration file.
3. Insert the JFrog MCP Server entry:

{
  "mcpServers": {
    "jfrog": {
      "command": "npx",
      "args": ["@jfrog/mcp-jfrog@latest"]
    }
  }
}

4. Save and restart Cursor.
5. Check Cursor’s MCP integrations for successful registration.

Cline

1. Install Node.js and set up Cline.
2. Access the Cline configuration file.
3. Add the following MCP server configuration:

{
  "mcpServers": {
    "jfrog": {
      "command": "npx",
      "args": ["@jfrog/mcp-jfrog@latest"]
    }
  }
}

4. Save your configuration and restart Cline.
5. Validate the connection through Cline’s UI or CLI.

Securing API Keys

Always secure API keys using environment variables. Example configuration:

{
  "mcpServers": {
    "jfrog": {
      "command": "npx",
      "args": ["@jfrog/mcp-jfrog@latest"],
      "env": {
        "JFROG_API_KEY": "${env.JFROG_API_KEY}"
      },
      "inputs": {
        "baseUrl": "https://your.jfrog.instance"
      }
    }
  }
}

Replace "JFROG_API_KEY" and "baseUrl" with your actual environment variable and JFrog instance URL.

How to use this MCP inside flows

Using MCP in FlowHunt

To integrate MCP servers into your FlowHunt workflow, start by adding the MCP component to your flow and connecting it to your AI agent:

Click on the MCP component to open the configuration panel. In the system MCP configuration section, insert your MCP server details using this JSON format:

{
  "jfrog": {
    "transport": "streamable_http",
    "url": "https://yourmcpserver.example/pathtothemcp/url"
  }
}

Once configured, the AI agent is now able to use this MCP as a tool with access to all its functions and capabilities. Remember to change “jfrog” to whatever the actual name of your MCP server is and replace the URL with your own MCP server URL.

Overview

Our opinion

The JFrog MCP Server offers robust integration for repository and artifact management, with a well-documented toolset and clear setup instructions. However, it lacks documentation on prompt templates, explicit MCP resources, and advanced MCP features like roots or sampling. Overall, it is highly useful for DevOps automation but may require enhancements for broader MCP compatibility.

MCP Score: 7/10. It scores well for practical tools, licensing, and adoption but is missing some advanced MCP documentation and features.

MCP Score