# Connecting to the server

> Once the server is deployed, to connect to it when using the Computer Vision activities, you must change the endpoints for the CV Screen Scope and UiPath Screen OCR activities.

Once the server is deployed, to connect to it when using the Computer Vision activities, you must change the endpoints for the CV Screen Scope and UiPath Screen OCR activities.

## Changing the endpoints on activity level

On activity level in your UiPath Studio project, you need to change:

* the **URL** property value of the CV Screen Scope activity, and
* the **Endpoint** property value of the UiPath Screen OCR activity

to `http://[MACHINE_URL]:[PORT]`, where `[MACHINE_URL]` is the address of the machine where the server is deployed, and `[PORT]` is the unique port on which the Computer Vision Server is set up.

For example, if the URL of your machine is `k80-windows.azure.com`, and the port you have chosen to work with is 8501, then the value of the property should look like `http://k80-windows.azure.com:8501`.

:::important
The API key property inside the CV Screen Scope can be left blank for on-premises deployment.
:::

## Changing the endpoints on project level

The default URLs can also be changed from the [Project Settings](https://docs.uipath.com/studio/standalone/2023.10/user-guide/about-automation-projects#adjusting-project-settings) page.

### Changing the endpoint for CV Screen Scope

To change the endpoint for CV Screen Scope, go to **UiPath Studio** > your project > **Project Settings** > **Computer Vision** > **CV Screen Scope** > **Server** > **Run value/Debug value** > change `https://cv.uipath.com` to `http://[MACHINE_URL]:[PORT]`, where `[MACHINE_URL]` is the address of the machine where the server is deployed, and `[PORT]` is the unique port on which the Computer Vision Server is set up.

  ![docs image](https://dev-assets.cms.uipath.com/assets/images/ai-computer-vision/ai-computer-vision-docs-image-373896-20e6e863-2e156e1b.png)

### Changing the endpoint for UiPath Screen OCR

To change the endpoint for UiPath Screen OCR, go to **UiPath Studio** > your project > **Project Settings** > **OCR** > **UiPath Screen OCR** > **Endpoint** > **Run value/Debug value** > change `https://ocr.uipath.com` to `http://[MACHINE_URL]:[PORT]`, where `[MACHINE_URL]` is the address of the machine where the server is deployed, and `[PORT]` is the unique port on which the Computer Vision Server is set up.

  ![docs image](https://dev-assets.cms.uipath.com/assets/images/ai-computer-vision/ai-computer-vision-docs-image-373892-6fb83e5a-53d2a14e.png)

## Enabling HTTPS

To encrypt communication, you can add a reverse proxy (for example, [NGINX](https://docs.nginx.com/)) in front of the container and configure TLS or SSL on this layer.

After enabling HTTPS communication, you need to change the endpoint for CV Screen Scope and for UiPath Screen OCR from `https://cv.uipath.com` to `https://[MACHINE_URL]:[PORT]`, where `[MACHINE_URL]` is the address of the machine where the server is deployed, and `[PORT]` is the unique port on which the Computer Vision Server is set up.

## Opening the default port

:::important
Make sure you have the port that is used by the Computer Vision activities (default `8501`) open on the machine the model is deployed on. For client machines outside of the domain, the DNS is used instead.
:::

To open the port on the server machine, you have to run the following console commands, replacing `[PORT]` with the actual port you want to use and `[your-default-zone]` with your system's zone (by default `public`):

```
apt install firewalld
            systemctl enable firewalld
            firewall-cmd --zone=[your-default-zone] --permanent --add-port=[PORT]/tcp
            firewall-cmd --reload
```

## Changing the default port

The default port exposed by the server is `8501`.

To change the default port, you must start the server with a different command.

Change the `-p 8501:5000` flag to `-p [NEW_PORT]:5000`, where `[NEW_PORT]` is the port you want to use.

## Restarting the server

To change the port to `5000`, the restarting server command for Linux looks like this:

```
podman run -d
-p 8501:5000
--hooks-dir=/usr/share/containers/oci/hooks.d/ \--security-opt=label=disable --device=nvidia.com/gpu=all
--restart unless-stopped
--name controls_detection
container controls_detection eula=accept
```