mcp-jfrog
Model Context Protocol (MCP) Server for the JFrog Platform API, enabling repository management, build tracking, release lifecycle management, and more.
claude mcp add --transport stdio jfrog-mcp-jfrog npx -y jfrog-mcp-jfrog
How to use
The JFrog MCP Server (experimental) provides a Model Context Protocol (MCP) interface to interact with the JFrog Platform. It exposes capabilities to manage repositories (local, remote, and virtual), query and track builds, monitor runtime clusters and images, access catalog information including package details and vulnerabilities, and perform AQL-based searches across Artifactory data. Typical usage includes checking platform readiness, creating repositories, listing builds, querying environments and projects, and performing artifact searches via AQL. You can leverage the toolset to automate repository provisioning, monitor build activity, and surface security and compliance information from JFrog Artifactory and Xray within your MCP workflows.
How to install
Prerequisites:
- Node.js (for Node-based MCP) or the runtime specified by the deployment method you choose (see mcp_config for the command to run).
- Network access to your JFrog Platform endpoints and, if needed, API credentials.
Install and run (example using npm/npx):
- Install the MCP server package (via npm or npx):
- If using npx: npx -y jfrog-mcp-jfrog
- If you have a local copy: npm install jfrog-mcp-jfrog
- Configure environment variables (see additional_notes for details).
- Start the MCP server using the command in mcp_config (or your deployment mechanism):
- npx -y jfrog-mcp-jfrog
- Verify the server is up by calling its health or status endpoints as documented in the repository.
Notes:
- If you are deploying in Docker or a virtual environment, adapt the command accordingly and mount necessary config files or environment variables.
Additional notes
Environment variables and configuration tips:
- JFROG_BASE_URL: Base URL for the JFrog Platform API (e.g., https://myjfrog.example.com).
- JFROG_API_TOKEN or JFROG_USERNAME/JFROG_PASSWORD: Credentials for authenticating with JFrog Platform APIs.
- JFROG_INSECURE_SKIP_TLS: Set to true to skip TLS certificate verification in development environments (not recommended for production).
- MCP_LOG_LEVEL: Logging level for the MCP server (e.g., info, debug).
- Optional: SPECIFICALLY_YOU_NEED_FOR_AQL: Any custom AQL port or proxy settings if your Artifactory requires it.
Common issues:
- Network routing errors when reaching JFrog Platform APIs: verify base URL and tokens, ensure host firewall rules allow traffic.
- Permissions errors when creating repositories or projects: ensure the API token has sufficient privileges.
- TLS/SSL issues in development environments: consider setting JFROG_INSECURE_SKIP_TLS to true temporarily and use valid certificates in production.
Configuration considerations:
- You can extend the MCP server by enabling more endpoints (builds, environments, projects) as described in the repository documentation.
- For large environments, consider pagination and rate limits when listing builds or runtime clusters.
Related MCP Servers
mcp-graphql
Model Context Protocol server for GraphQL
mcp-google-map
A powerful Model Context Protocol (MCP) server providing comprehensive Google Maps API integration with LLM processing capabilities.
systemprompt-code-orchestrator
MCP server for orchestrating AI coding agents (Claude Code CLI & Gemini CLI). Features task management, process execution, Git integration, and dynamic resource discovery. Full TypeScript implementation with Docker support and Cloudflare Tunnel integration.
pluggedin-app
The Crossroads for AI Data Exchanges. A unified, self-hostable web interface for discovering, configuring, and managing Model Context Protocol (MCP) servers—bringing together AI tools, workspaces, prompts, and logs from multiple MCP sources (Claude, Cursor, etc.) under one roof.
rohlik
MCP server that lets you shop groceries across the Rohlik Group platforms (Rohlik.cz, Knuspr.de, Gurkerl.at, Kifli.hu, Sezamo.ro)
mcp -js
MCP server that exposes YepCode processes as callable tools for AI platforms. Securely connect AI assistants to your YepCode workflows, APIs, and automations.