Connecting LLMs and AI Agents to Projectal

Modified on Tue, 18 Aug at 7:12 PM

Connecting your AI assistant to Projectal takes less than a minute. You only need one piece of information: your unique Projectal MCP Server URL. This can be found on the Management screen by clicking the MCP Server button. If you don't have access to the Management screen, then contact your system administrator of Projectal.


Prerequisites 

You will need the Projectal MCP Server URL. This can be found on the Management screen by clicking the MCP Server button. If you don't have access to the Management screen, then contact your system administrator of Projectal.


You will need to have an MCP-compatible AI assistant installed on your computer or cloud-based. There are many to choose from. Examples are Claude Desktop, Cursor, and ChatGPT


Step 1. Locate your AI Assistant Settings

Open your AI client tool (e.g., Claude Desktop) and open Settings. Look for the MCP, Tools, or Integrations tab.


Step 2. Add a New MCP Server

Click Add New Server (or edit your app's json file if your AI client tool uses file-based configuration). Select SSE / HTTP as the transport type.


Step 3. Enter Server Details

Set the connection details using your organization's endpoint:

  • Name: Projectal
  • URL: Enter your Projectal MCP Server URL


Step 4. Authenticate & Connect

Click Connect or Save. Your AI client tool will automatically reach out to the MCP server URL. If prompted, complete the secure OAuth or API sign-in using your regular Projectal credentials.


Step 5. Verify the Connection

Once connected, look for a green active status or a hammer icon displaying Projectal's toolset (e.g., get_projects, search_resources, get_staff_schedules).


Sample Configuration snippet 

If your AI client tool uses a JSON configuration file (such as claude_desktop_config.json), then add Projectal under the mcpServers object:


{  

  "mcpServers": {    

    "projectal": {

      "url": "(add your Projectal MCP server URL here)"    

    }  

  } 


Test Your Setup

Once connected, test the integration in a new chat by asking natural language questions about your workspace:

  • "What active projects do we currently have in Projectal?"
  • "List all active staff."
  • "Which staff are currently idle?"

Was this article helpful?

That’s Great!

Thank you for your feedback

Sorry! We couldn't be helpful

Thank you for your feedback

Let us know how can we improve this article!

Select at least one of the reasons
CAPTCHA verification is required.

Feedback sent

We appreciate your effort and will try to fix the article