Jfrog Mcp Server

What is Jfrog Mcp Server about?

Jfrog Mcp Server enables programmatic interaction with JFrog Artifactory, Xray, Distribution, and Runtime services. It exposes a rich set of tools that allow creation and management of repositories, retrieval of build and runtime information, execution of AQL searches, package catalog queries, and vulnerability summaries.

How to use Jfrog Mcp Server?

1. Install – Run the server with npm using npx -y @jfrog/mcp-jfrog (or via Docker). Set the required environment variables JFROG_ACCESS_TOKEN and JFROG_URL.
2. Configure transport – By default the server uses STDIO; for web‑based clients set TRANSPORT=sse and expose the port (default 8080).
3. Connect – Clients connect to the /sse endpoint (SSE mode) or send JSON‑RPC messages to /messages.
4. Call tools – Use the JSON‑RPC method names (e.g., list_repositories, create_local_repository, jfrog_get_package_info) with the documented parameters.

Key features of Jfrog Mcp Server

• Repository management: create, list, and configure local, remote, and virtual repositories.
• Build management: list builds and fetch detailed build information.
• Runtime management: enumerate runtime clusters and running container images.
• Access control: list projects, environments, and create new projects.
• Catalog & curation: fetch package metadata, versions, vulnerabilities, and curation status for multiple ecosystems (npm, PyPI, Maven, etc.).
• Xray integration: obtain per‑artifact vulnerability severity summaries.
• AQL execution: run powerful Artifactory queries with pagination, sorting, and field selection.
• SSE transport mode with connection tracking, health endpoint, and automatic reconnection.

Use cases of Jfrog Mcp Server

• Automating CI/CD pipelines that need to create repositories on‑the‑fly.
• Building custom dashboards that display build health, runtime cluster status, and security posture.
• Integrating third‑party tools (e.g., Claude, Cursor) to query JFrog data via natural‑language interfaces.
• Conducting security audits by pulling vulnerability summaries for a set of artifacts.
• Managing multi‑project environments programmatically for large organizations.

FAQ from the Jfrog Mcp Server

Q: Do I need a JFrog token? A: Yes. Set JFROG_ACCESS_TOKEN with a token that has the required scopes for repository, build, and Xray APIs.

Q: Can I run the server in production? A: The project is experimental. For production workloads JFrog recommends the official managed MCP server.

Q: Which transport should I use? A: STDIO works for CLI integrations; SSE (TRANSPORT=sse) is recommended for web‑based clients that need persistent connections.

Q: How do I limit the number of reconnection attempts? A: Configure MAX_RECONNECT_ATTEMPTS and RECONNECT_DELAY_MS environment variables.

Q: Is Docker required? A: No. You can run the server directly with Node.js or via Docker if you prefer container isolation.

JFrog MCP Server (🧪 Experimental)

Model Context Protocol (MCP) Server for the JFrog Platform API, enabling repository management, build tracking, release lifecycle management, and more.

https://github.com/user-attachments/assets/aca3af2b-f294-41c8-8727-799a019a55b5

Disclaimer

This is an experimental project intended to demonstrate JFrog's capabilities with MCP. It is not officially supported or verified by JFrog.

Update (2025):
JFrog now provides an official, secure, and remotely hosted MCP server for seamless integration with the JFrog Platform.
This managed MCP server is maintained by JFrog and is recommended for production use, offering enhanced security, reliability, and support.

Learn more and get started here:
👉 JFrog MCP Server Documentation

Features

• Repository Management: Create and manage local, remote, and virtual repositories
• Build Tracking: List and retrieve build information
• Runtime Monitoring: View runtime clusters and running container images
• Mission Control: View associated JFrog Platform instances
• Artifact Search: Execute powerful AQL queries to search for artifacts and builds
• Catalog and Curation: Access package information, versions, vulnerabilities, and check curation status
• Xray: Access scan artifacts summary, group by severity per artifact

Tools

1. check_jfrog_availability

   • Check if JFrog platform is ready and functioning
   • Returns: Platform readiness status

2. create_local_repository

   • Create a new local repository in Artifactory
   • Inputs:
     • key (string): Repository key
     • rclass (string): Repository class (must be "local")
     • packageType (string): Package type of the repository
     • description (optional string): Repository description
     • projectKey (optional string): Project key to assign the repository to
     • environments (optional string[]): Environments to assign the repository to
   • Returns: Created repository details

3. create_remote_repository

   • Create a new remote repository in Artifactory to proxy external package registries
   • Inputs:
     • key (string): Repository key
     • rclass (string): Repository class (must be "remote")
     • packageType (string): Package type of the repository
     • url (string): URL to the remote repository
     • username (optional string): Remote repository username
     • password (optional string): Remote repository password
     • description (optional string): Repository description
     • projectKey (optional string): Project key to assign the repository to
     • environments (optional string[]): Environments to assign the repository to
     • Many other optional parameters for specific repository configurations
   • Returns: Created repository details

4. create_virtual_repository

   • Create a new virtual repository in Artifactory that aggregates multiple repositories
   • Inputs:
     • key (string): Repository key
     • rclass (string): Repository class (must be "virtual")
     • packageType (string): Package type of the repository
     • repositories (string[]): List of repository keys to include in the virtual repository
     • description (optional string): Repository description
     • projectKey (optional string): Project key to assign the repository to
     • environments (optional string[]): Environments to assign the repository to
     • Other optional parameters for specific repository configurations
   • Returns: Created repository details

5. list_repositories

   • List all repositories in Artifactory with optional filtering
   • Inputs:
     • type (optional string): Filter repositories by type (local, remote, virtual, federated, distribution)
     • packageType (optional string): Filter repositories by package type
     • project (optional string): Filter repositories by project key
   • Returns: List of repositories matching the filters

6. set_folder_property

   • Set properties on a folder in Artifactory, with optional recursive application
   • Inputs:
     • folderPath (string): Path to the folder where properties should be set
     • properties (object): Key-value pairs of properties to set
     • recursive (optional boolean): Whether to apply properties recursively to sub-folders
   • Returns: Operation result

7. execute_aql_query

   • Execute an Artifactory Query Language (AQL) query to search for artifacts, builds, or other entities in JFrog Artifactory
   • Inputs:
     • query (string): The AQL query to execute. Must follow AQL syntax (e.g., items.find({"repo":"my-repo"}).include("name","path"))
     • domain (optional string): The primary domain to search in (items, builds, archive.entries, build.promotions, releases)
     • transitive (optional boolean): Whether to search in remote repositories
     • limit (optional number): Maximum number of results to return
     • offset (optional number): Number of results to skip
     • include_fields (optional string[]): Fields to include in the results
     • sort_by (optional string): Field to sort results by
     • sort_order (optional string): Sort order (asc or desc)
   • Returns: Search results with metadata

8. list_jfrog_builds

   • Return a list of all builds in the JFrog platform
   • Returns: List of builds

9. get_specific_build

   • Get details for a specific build by name
   • Inputs:
     • buildName (string): Name of the build to retrieve
     • project (optional string): Project key to scope the build search
   • Returns: Build details

10. list_jfrog_runtime_clusters

    • Return a list of all runtime clusters in the JFrog platform
    • Inputs:
      • limit (optional integer): The maximum number of clusters to return
      • next_key (optional string): The next key to use for pagination
    • Returns: List of runtime clusters

11. get_jfrog_runtime_specific_cluster

    • Return a runtime cluster by ID
    • Inputs:
      • clusterId (integer): The ID of the cluster to retrieve
    • Returns: Cluster details

12. list_jfrog_running_images

    • List all running container images across runtime clusters with their security and operational status
    • Inputs:
      • filters (optional string): Filters to apply
      • num_of_rows (optional integer): Number of rows to return
      • page_num (optional integer): Page number
      • statistics (optional boolean): Whether to include statistics
      • timePeriod (optional string): Time period to query
    • Returns: List of running images

13. list_jfrog_environments

    • Get a list of all environments types in the JFrog platform with their details
    • Inputs:
    • Returns: List of environments

14. list_jfrog_projects

    • Get a list of all projects in the JFrog platform with their details
    • Inputs:
    • Returns: List of projects

15. get_specific_project

    • Get detailed information about a specific project in the JFrog platform
    • Inputs:
      • project_key (string): The unique key of the project to retrieve
    • Returns: Project details

16. create_project

    • Create a new project in the JFrog platform
    • Inputs:
      • project_key (string): Unique identifier for the project
      • display_name (string): Display name of the project
      • description (string): Description of the project
      • admin_privileges (object): Administrative privileges for the project
      • storage_quota_bytes (number): Storage quota in bytes (-1 for unlimited)
    • Returns: Created project details

17. jfrog_get_package_info

    • Get publicly available information about a software package
    • Inputs:
      • type (string): The type of package (pypi, npm, maven, golang, nuget, huggingface, rubygems)
      • name (string): The name of the package, as it appears in the package repository
      • version (optional string): The version of the package (default: "latest")
    • Returns: Package information including description, latest version, license, and URLs

18. jfrog_get_package_versions

    • Get a list of versions of a publicly available package with publication dates
    • Inputs:
      • type (string): The type of package (pypi, npm, maven, golang, nuget, huggingface, rubygems)
      • name (string): The name of the package, as it appears in the package repository
    • Returns: List of package versions with publication dates

19. jfrog_get_package_version_vulnerabilities

    • Get a list of known vulnerabilities affecting a specific version of an open source package
    • Inputs:
      • type (string): The type of package (pypi, npm, maven, golang, nuget, huggingface, rubygems)
      • name (string): The name of the package, as it appears in the package repository
      • version (optional string): The version of the package (default: "latest")
      • pageSize (optional number): Number of vulnerabilities to return per page (default: 10)
      • pageCount (optional number): Number of pages to return (default: 1)
    • Returns: List of vulnerabilities affecting the specified package version

20. jfrog_get_vulnerability_info

    • Get detailed information about a specific vulnerability, including affected packages and versions
    • Inputs:
      • cve_id (string): The CVE ID or vulnerability identifier to look up
      • pageSize (optional number): Number of vulnerabilities to return per page (default: 10)
      • pageCount (optional number): Number of pages to return (default: 1)
    • Returns: Detailed vulnerability information and affected packages

21. jfrog_get_package_curation_status

    • Check the curation status of a specific package version
    • Inputs:
      • packageType (string): The type of package (pypi, npm, maven, golang, nuget, huggingface, rubygems)
      • packageName (string): The name of the package, as it appears in the package repository
      • packageVersion (string): The version of the package, as it appears in the package repository
    • Returns: Curation status (approved, blocked, or inconclusive)

22. jfrog_get_artifacts_summary
    • Get artifacts issues summary in a repository or build, categorized and counted by severity (Low, Medium, High, Critical, Unkown)
    • Inputs:
      • paths (string array): An array of paths to the artifacts from which to create the summary from
    • Returns: A summary based on vulnerability count per severity for each artifact in the provided array plus the total issues

Setup

Installing via Smithery

To install mcp-jfrog for Claude Desktop automatically via Smithery:

npx -y @smithery/cli install @jfrog/mcp-jfrog --client claude

Prerequisites

• Node.js v18 or higher
• Docker (if using Docker deployment, See Docker Deployment )
• A valid JFrog platform instance with appropriate permissions
• Access to create and manage access tokens in your JFrog platform instance

Environment Variables

• JFROG_ACCESS_TOKEN: Your JFrog access token (required)
• JFROG_URL: Base URL for your JFrog platform (required)
• TRANSPORT: Transport mode to use, set to 'sse' to enable SSE transport (default: stdio)
• PORT: Port number to use for SSE transport (default: 8080)
• CORS_ORIGIN: CORS origin allowed for SSE connections (default: '*')
• LOG_LEVEL: Logging level: DEBUG, INFO, WARN, ERROR (default: INFO)
• MAX_RECONNECT_ATTEMPTS: Maximum number of reconnection attempts for SSE server (default: 5)
• RECONNECT_DELAY_MS: Base delay in milliseconds between reconnection attempts (default: 2000)

JFrog Token (JFROG_ACCESS_TOKEN)

To use this MCP server, you need to create a JFrog Access Token or use an identity token with appropriate permissions:

For information on how to create a JFrog Token, please refer to the JFrog official documentations:

• Identity Tokens

• Access Tokens

JFrog URL (JFROG_URL)

Your JFrog platform instance URL (e.g. https://acme.jfrog.io)

SSE Transport Features

The SSE transport mode includes the following features:

• Connection Management: Each SSE connection is tracked with a unique ID, allowing clients to maintain state across reconnection attempts.
• Structured Logging: Detailed logs with timestamps, severity levels, and relevant contextual information.
• Connection Resilience: Automatic reconnection attempts with exponential backoff if the server fails to start.
• Health Endpoint: A /health endpoint that returns server status information.
• Connection Tracking: Real-time tracking of active connections with periodic statistics logging.
• Performance Metrics: Execution time tracking for tool operations and HTTP requests.

When using SSE mode:

1. Clients should connect to the /sse endpoint, optionally providing a connectionId query parameter for session tracking.
2. Client requests should be sent to the /messages endpoint with the same connectionId as a query parameter.
3. The server will respond with server-sent events through the established SSE connection.

Example client connection with connection ID:

GET /sse?connectionId=client123

Example client request:

POST /messages?connectionId=client123
Content-Type: application/json

{
  "jsonrpc": "2.0",
  "method": "listTools",
  "id": 1
}

How to build

Clone the repo to your local machine using git clone and cd into the project directory:

git clone git@github.com:jfrog/mcp-jfrog.git

cd mcp-jfrog

Build as a Docker image:

docker build -t mcp/jfrog -f Dockerfile .

Build as an npm module:

npm i && npm run build

Usage

npm

{
  "mcpServers": {
    "MCP-JFrog": { 
      "command": "npm",
      "args": [
        "exec",
        "-y",
        "github:jfrog/mcp-jfrog"
      ],
      "env": {
        "JFROG_ACCESS_TOKEN": "ACCESS_TOKEN",
        "JFROG_URL": "https://<YOUR_JFROG_INSTANCE_URL>"
      }
    }
  },
  "mcp-local-dev":{
      "command": "node",
      "args": [
        "/<ABSOLUT_PATH_TO>/mcp-jfrog/dist/index.js"
      ],
      "env": {
        "JFROG_ACCESS_TOKEN": "<ACCESS_TOKEN>>",
        "JFROG_URL": "<JFROG_URL>"
      }
    }
}

Docker

{
  "mcpServers": { 
    "jfrog": {
      "command": "docker",
      "args": [
        "run",
        "--rm",
        "-i",
        "-e",
        "JFROG_ACCESS_TOKEN",
        "-e",
        "JFROG_URL",
        "mcp/jfrog"
      ],
      "env": {
        "JFROG_ACCESS_TOKEN": "<YOUR_TOKEN>",
        "JFROG_URL": "https://your-instance.jfrog.io"
      },
      "serverUrl": "http://localhost:8080/sse"
    }
  }
}

SSE Transport Mode

To use the JFrog MCP Server with SSE transport mode (useful for web interfaces like Cursor's webview):

{
  "mcpServers": { 
    "jfrog-sse": {
      "command": "docker",
      "args": [
        "run",
        "--rm",
        "-p",
        "8080:8080",
        "-e",
        "TRANSPORT=sse",
        "-e",
        "PORT=8080",
        "-e",
        "CORS_ORIGIN=*",
        "-e",
        "LOG_LEVEL=INFO",
        "-e",
        "MAX_RECONNECT_ATTEMPTS=5",
        "-e",
        "RECONNECT_DELAY_MS=2000",
        "-e",
        "JFROG_ACCESS_TOKEN",
        "-e",
        "JFROG_URL",
        "mcp/jfrog"
      ],
      "env": {
        "JFROG_ACCESS_TOKEN": "<YOUR_TOKEN>",
        "JFROG_URL": "https://your-instance.jfrog.io",
        "serverUrl": "http://localhost:8080/sse"
      }
    }
  }
}

Note: For SSE mode, you need to add the serverUrl parameter pointing to your SSE endpoint, and expose the port used by the server (-p 8080:8080).

Add the following to your claude_desktop_config.json:

Docker

{
  "mcpServers": { 
    "jfrog": {
      "command": "docker",
      "args": [
        "run",
        "--rm",
        "-i",
        "-e",
        "JFROG_ACCESS_TOKEN",
        "-e",
        "JFROG_URL",
        "mcp/jfrog"
      ],
      "env": {
        "JFROG_ACCESS_TOKEN": "<YOUR_TOKEN>",
        "JFROG_URL": "https://your-instance.jfrog.io" // Your JFrog platform URL
      },
      "serverUrl": "http://localhost:8080/sse"
    }
  }
}

npm

{
"mcpServers": {
    "MCP-JFrog": { 
      "command": "npm",
      "args": [
        "exec",
        "-y",
        "github:jfrog/mcp-jfrog"
      ],
      "env": {
        "JFROG_ACCESS_TOKEN": "ACCESS_TOKEN",
        "JFROG_URL": "https://<YOUR_JFROG_INSTANCE_URL>"
      }
    }
  }
}

SSE Transport Mode

For Claude Desktop with SSE transport:

{
  "mcpServers": { 
    "jfrog-sse": {
      "command": "docker",
      "args": [
        "run",
        "--rm",
        "-p",
        "8080:8080",
        "-e",
        "TRANSPORT=sse",
        "-e",
        "PORT=8080",
        "-e",
        "CORS_ORIGIN=*",
        "-e",
        "LOG_LEVEL=INFO",
        "-e",
        "MAX_RECONNECT_ATTEMPTS=5",
        "-e",
        "RECONNECT_DELAY_MS=2000",
        "-e",
        "JFROG_ACCESS_TOKEN",
        "-e",
        "JFROG_URL",
        "mcp/jfrog"
      ],
      "env": {
        "JFROG_ACCESS_TOKEN": "<YOUR_TOKEN>",
        "JFROG_URL": "https://your-instance.jfrog.io",
        "serverUrl": "http://localhost:8080/sse"
      }
    }
  }
}

</details>


## License

This MCP server is licensed under the Apache License 2.0. This means you are free to use, modify, and distribute the software, subject to the terms and conditions of the Apache License 2.0. For more details, please see the LICENSE.md file in the project repository.