> ## Documentation Index
> Fetch the complete documentation index at: https://explore.airia.com/llms.txt
> Use this file to discover all available pages before exploring further.

# How to Add a Deployment to an Agent

> Attach a Deployment to an AI Model step so the agent can call its tools.

Attaching a Deployment to an AI Model step gives that step access to the Deployment's tools, so the model can call them while generating a response. You can attach a Deployment you created yourself, or one an admin already set up for your project.

This is separate from connecting a Gateway to an external MCP client. See [Deployments vs. Gateways](/mcps/admin-controls/deployments-vs-gateways) if you're not sure which one you need.

## Attach a Deployment to a Step

<Steps>
  <Step title="Open the AI Model step">
    In your agent, select the AI Model step you want to give tool access to.
  </Step>

  <Step title="Open the MCP Servers tab">
    In the step's side panel, open the **MCP Servers** tab.
  </Step>

  <Step title="Select the Deployments you want">
    Click **Select MCP server deployments**. A searchable list shows every Deployment available to you: anything created in your current project, plus any Deployment that isn't tied to a specific project. Check as many as you want to use on this step; there's no limit.
  </Step>

  <Step title="Save the agent">
    Save. The step now has access to every tool you've enabled on each Deployment you added.
  </Step>
</Steps>

## Create a Deployment Without Leaving the Canvas

If you have admin permissions, a **Create new deployment** option appears below the selector so you can pick an app and set it up on the spot, without navigating away from your agent. Anyone else building an agent can only choose from Deployments that already exist.

See [Gateway/Deployment Creation](/mcps/admin-controls/gateway-deployment-creation) for the full setup flow, or ask an admin to create one for your project if you don't see the option.

## Choose Which Tools a Step Can Use

Click into an attached Deployment to see every tool it has, each with its own on/off toggle, plus **Enable All** and **Disable All** for quick changes. A running count shows how many tools are active out of the total available.

This selection is scoped to the step you're editing, not to the Deployment itself. Turning a tool on or off here doesn't change what's enabled on the original Deployment. Different steps, in this agent or any other, can each enable a different subset of the same Deployment's tools, so you can reuse one Deployment across several agents while giving each one only the access it actually needs.

<Tip>
  As with Gateways, every tool you enable adds to what the model has to read before it can respond. Turn on only the tools a given step actually uses, even if the underlying Deployment has more available.
</Tip>

## Authentication

A Deployment's detail view shows a credential banner that determines whether its tools work right away:

* **End-user credentials.** Every tool toggle stays disabled until you click **Authenticate** and connect your own account, even if someone else already connected the same app.
* **Tenant credentials.** Tools work for everyone the moment the Deployment is attached.

See [Tenant vs. Personal Level App Credentials](/mcps/admin-controls/tenant-vs-personal-app-credentials) for how these levels work.

<Warning>
  If an agent with a Personal-credential Deployment is shared with other users, each of them needs to authenticate their own account before that Deployment's tools work for them. Sharing the agent doesn't share your sign-in.
</Warning>

## Remove a Deployment from a Step

Open the **MCP Servers** tab and remove the Deployment's card. This only detaches it from this step. The Deployment itself isn't touched, so it's still there to attach to this or any other agent later.

## Test Your Enabled Tools

There's no separate preview for which tools are reachable. Airia relays the tools listed by the origin server, and some servers, even after authentication, list but restrict access to certain tools depending on your account permissions.

Instead, run the agent in the **Playground** and send a message that should trigger one of your enabled tools. When the model calls it, a tool execution card appears in the response showing which tool ran and whether it succeeded, so you can confirm your setup before publishing.

## Troubleshooting

* **A Deployment I expect to see isn't in the selector.** Confirm it's scoped to your current project or to all projects. Ask an admin if you still don't see it.
* **A step shows a warning where a Deployment used to be.** The attached Deployment was deleted elsewhere. Remove the stale reference and attach a replacement if the step still needs those tools.

## Related Resources

<CardGroup cols={2}>
  <Card title="Deployments vs. Gateways" icon="scale-balanced" href="/mcps/admin-controls/deployments-vs-gateways">
    Decide which one fits before you build
  </Card>

  <Card title="Gateway/Deployment Creation" icon="plug" href="/mcps/admin-controls/gateway-deployment-creation">
    Build a Deployment step by step
  </Card>

  <Card title="Tenant vs. Personal Level App Credentials" icon="key" href="/mcps/admin-controls/tenant-vs-personal-app-credentials">
    See how each credential level works
  </Card>

  <Card title="Credential Recovery" icon="rotate" href="/mcps/end-user-usage/credential-recovery">
    Fix a connection that stops authenticating
  </Card>
</CardGroup>