Server deployments in Metorial define which integrations are available to your AI agents. This guide explains how to configure them.

What are Server Deployments?

Server deployments are collections of MCP servers (integrations) that you want to make available to your application. Each deployment can include multiple integrations like GitHub, Slack, Google Calendar, and more.

Creating a Server Deployment

1. Log in to Metorial: Access your Metorial dashboard.

2. Navigate to Deployments: Find the "Server Deployments" or "Integrations" section.

3. Create new deployment: Click "Create Deployment" or "New Deployment".

4. Select integrations: Choose which integrations you want to include (e.g., GitHub, Google Calendar, Slack).

5. Configure settings: Set up authentication and permissions for each integration.

6. Save and copy ID: After saving, copy your deployment ID.

Using Server Deployments in Code

Reference your deployment ID when creating a provider session:

import { metorialAiSdk } from '@metorial/ai-sdk';
import { Metorial } from 'metorial';

const metorial = new Metorial({
  apiKey: 'your-metorial-api-key'
});

await metorial.withProviderSession(
  metorialAiSdk,
  { 
    serverDeployments: ['your-server-deployment-id']
  },
  async session => {
    // Your AI SDK code here
    // session.tools contains all tools from your deployment
  }
);

Multiple Deployments

You can use multiple deployments by passing an array of deployment IDs:

{
  serverDeployments: [
    'deployment-id-1',
    'deployment-id-2'
  ]
}

This combines all integrations from both deployments into a single session.