Deploying your first MCP server

Learn how to deploy an MCP server in your Metorial project

The first step in allowing your AI integrations to access external tools via Metorial lies in deploying a MCP server.

What you’ll learn:

• How to deploy an MCP server

Before you start:

• Complete the Introduction guide

Deploying an MCP server

MCP servers in Metorial provide tools and resources to AI assistants through the Model Context Protocol. This guide will walk you through deploying your server and making it accessible to AI applications.

1. Open the Server Page

   Navigate to the Servers section in the dashboard and select the GitHub MCP server.

   
2. Create a Server Deployment

   Click Create Deployment to set up a new deployment of the MCP server.

   
3. Configure Deployment Settings

   Set up your deployment configuration by choosing a clear, descriptive name for the deployment and generating a GitHub Personal Access Token. Store the token securely. For detailed steps on creating and managing your token, refer to the GitHub documentation.

   
4. Your Server is Ready

   The server has now been deployed and is ready to use!

   

What’s Next?

🎉 You’ve successfully deployed your first MCP server! Next, we’ll guide you through testing your server’s capabilities.

Next Up: How to test an MCP server

Learn how to test an MCP server using the Explorer.