Try JFrog
Guides
Contact SupportTry JFrog
  1. MCP REGISTRY
  2. Manage MCP Servers

Configure and Enable Pre-built MCP Servers

Configure and enable pre-built MCP servers in the JFrog MCP Registry for a project.

Allow MCP Servers

Allow a curated public MCP server for a specific project in the JFrog Platform so developers can use it through the Agent Guard. Review server details, add it to the project registry, define tool policies, and configure required variables.

To configure a pre-built MCP server for a project:

Step 1: Select and Analyze

  1. In the JFrog Platform, navigate to AI/ML > Discovery > MCP Servers. Available MCP servers are displayed according to categories: Local, Remote, and Custom.

    📘

    Note

    This procedure describes how to configure and allow local and remote pre-built (public) MCP servers. For information about allowing custom MCP servers, see Custom MCP Servers.

    For each category, only a few MCPs are displayed by default. Click See All at the right side of the category to see all the MCP servers of that type.

  2. Click on an MCP card to open the MCP Server Details pane.

  3. Review the available tabs to ensure the tool is safe and usable:

    For local MCP servers only:

    • MCP Server Info: Displays general information about the MCP Server.
    • Config: Displays Environment Variables, for example, if the MCP requires API keys or runtime arguments.

    For local and remote MCP servers:

    • Identified Tools: Displays an AI-generated list of tools predicted to be in the package. This is a discovered suggestion list, not a final manifest. You can also see for which projects the MCP server is already allowed (Allowed in project field).
📘

Note

You can only allow the MCP to one project at a time. To allow it for additional projects, repeat the procedure for the other projects.

Step 2: Add to Registry

  1. Click Add to Registry in the MCP Server Details pane.
  2. Select a Project: Choose the specific project context where this tool will be active.

Step 3: Define Tool Policy

  1. Choose how to govern the tools within this server. Select one of the following options:
    • Allow all tools: Automatically approves all current tools and any tools added to this server in future updates.
    • Select tools manually (Recommended):
  2. Click Next:
    • If you selected Allow all tools, proceed directly to Step 4: Configure Required Variables.
    • If you selected Select tools manually, the Allow List and Deny List configuration pane is displayed. This enables you to define granular policies using static text and Regex patterns. For more information, see Configure Tool Policies.
      1. Select the tool patterns policy and tool pattern.
      2. Click Next.

Step 4: Configure Required Variables

Configure the Environment Variables and Runtime Arguments.

Step 5: Save Configuration

Click Save Configuration. The MCP now appears on the Registry page under AI/ML and is available for developers in that project.

Frequently Asked Questions

These questions cover common setup decisions when you allow a pre-built MCP server for a project.

plusFAQs
Q: What is the difference between local and remote pre-built MCP servers?

A: Local pre-built MCP servers are executable packages that run on the developer machine and are fetched through Artifactory via Agent Guard. Remote pre-built MCP servers are URL endpoints the agent connects to; Agent Guard enforces which remote servers are allowed. For more information, see Manage MCP Servers.

Q: Can I allow the same MCP server for multiple projects at once?

A: You can allow an MCP server to one project at a time. Repeat the procedure in Allow MCP Servers for each additional project.

Q: What is the difference between Allow all tools and Select tools manually?

A: Allow all tools approves every tool on the server now and in future updates. Select tools manually opens the Allow List and Deny List configuration so you can define granular policies using static text and Regex patterns. For more information, see Configure Tool Policies.

Q: Where do I find the MCP server after I save the configuration?

A: After you click Save Configuration, the MCP appears on the Registry page under AI/ML for the project you selected.

Related Topics

Updated about 1 month ago

Did this page help you?