Connect to the Tosca Cloud MCP server

Set up a connection between your AI assistant and the Tosca Cloud Model Context Protocol (MCP) server to access Tosca Cloud functionality directly from your development environment. This enables you to use natural language commands for your test automation tasks.

Before you start

Make sure you have the following before you connect to the Tosca Cloud MCP server:

  • Access to your Tosca Cloud tenant.

  • Node.js installed on your system.

  • An AI assistant that is compatible with MCP, such as Cursor AI, Visual Studio Code, Claude Code, or Claude Desktop.

  • If you're using Visual Studio Code, ensure your organization has the chat.mcp.enabled setting enabled.

The MCP server uses port 56874 for communication. Changing this port causes connection errors.

Configure your AI assistant

Configure your AI assistant to connect to the Tosca Cloud MCP server. The configuration steps depend on which AI assistant you're using.

To set up the Tosca Cloud MCP server connection in Cursor AI, follow these steps:

  1. Open the Cursor AI settings.

  2. Navigate to the MCP Tools section.

  3. Select New MCP Server to open a new mcp.json file.

  4. Add the ToscaCloudMcpServer configuration to your mcp.json file:

    Copy 
    {
      "mcpServers": {
        "ToscaCloudMcpServer": {
          "command": "npx",
          "args": [
            "-y",
            "mcp-remote@latest",
            "https://<your tenant name>.my.tricentis.com/default/_mcp/api/mcp",
            "56874",
            "--host",
            "127.0.0.1",
            "--static-oauth-client-info",
            "{\"client_id\":\"MCPServer\"}",
            "--static-oauth-client-metadata",
            "{\"scope\":\"tta\"}"
          ]
        }
      }
    }

    If you want to connect to a different workspace, replace default in the URL with your workspace ID.

  5. Save the file.

  6. Enable the MCP server you just configured.

  7. Sign in to Tosca Cloud, and complete authentication.

  8. Switch back to Cursor AI and look for a green circle and a list of available tools in the MCP server configuration.

To set up the Tosca Cloud MCP server connection in Visual Studio Code, follow these steps:

  1. Open your Visual Studio Code configuration file.

  2. Add the following configuration to your settings.json file:

    Copy 
    "chat.mcp.enabled": true,
    "mcp": {
      "servers": {
        "ToscaCloudMcpServer": {
          "command": "npx",
          "args": [
            "-y",
            "mcp-remote@latest",
            "https://<your tenant name>.my.tricentis.com/default/_mcp/api/mcp",
            "56874",
            "--host",
            "127.0.0.1",
            "--static-oauth-client-info",
            "{\"client_id\":\"MCPServer\"}",
            "--static-oauth-client-metadata",
            "{\"scope\":\"tta\"}"
          ]
        }
      }
    }

    If you want to connect to a different workspace, replace default in the URL with your workspace ID.

  3. Save the settings file.

  4. Sign in to Tosca Cloud, and complete authentication.

Check Your Connection Setup

Check your MCP connection here and find simple ways to fix it if it’s not working as you expected.

To verify that your MCP connection is working correctly, follow these steps:

  1. Open your AI assistant.

  2. Start a conversation with a simple command like: "Show me all available playlists "

  3. If the connection is successful, you should see a list of all your playlists.

If you're having issues connecting to the Tosca Cloud MCP server, check the following:

Issue

What to do

Port error: Cannot read properties of null (reading 'port')

Restart your AI assistant or terminate any running npx processes that could interfere with new connections.

Visual Studio Code says chat.mcp.enabled is blocked.

Ask your admin to enable MCP for your GitHub organization.

Authentication fails

- Clear your browser cache and retry

- Make sure you have access to the correct Workspace

- Verify that your MCP URL is correct

Fatal error: SyntaxError error when setting up the Tosca Cloud MCP server connection on Windows

Escape the quotes using backslashes:

Copy 
{
    "mcp": {
        "servers": {
            "ToscaCloudMcpServer": {
                "command": "npx",
                "args": [
                    "-y",
                    "mcp-remote@latest",
                    "https://<your tenant name>.my.tricentis.com/default/_mcp/api/mcp",
                    "56874",
                    "--host",
                    "127.0.0.1",
                    "--static-oauth-client-info",
                    "{\\\"client_id\\\":\\\"MCPServer\\\"}",
                    "--static-oauth-client-metadata",
                    "{\\\"scope\\\":\\\"tta\\\"}"
                ],
            }
        }
    }
}

Available MCP actions

Once connected, you can use the below MCP actions to interact with Tosca Cloud.

Create, analyze, and refine your test cases with these actions:

Action

Prompt examples

Scaffold test case

Create test case for user registration flow Scaffold regression test case

Analyze test case items

Improve my User registration test case

Show errors in the User registration test steps

Rename test case items

Rename steps to standard naming

Clean up test step labels

Search artifacts

Find all regression test cases

Search all steps made in the registration form

Get modules summary

List all modules

Show my active modules

Get failed test steps of failed cases

Show failed steps from last run

List failing steps this week

Organize your folders and assets in Tosca Cloud efficiently with these actions:

Action

Prompt examples

Create folder

Add folder named UI tests

Move folder

Move Regression folder under Release1 folder

Move asset (module, reusable test steps, test case)

Move test case Checkout Flow into Generic flows folder

Organize all Checkout Flows under Generic flows folder

Build, review, and monitor your playlists with these actions:

Action

Prompt examples

Add playlist

Create a playlist for all regression tests

Build playlist for smoke test

Get playlist IDs by name

Show the User registration flow playlist ID

Find Regression test playlist

Get recent playlist run logs

Show logs from last regression test

List the results for the latest playlist run

Create API messages in the API playground from your AI assistant with this action:

Action

Prompt examples

Create API message

Create an API message from this OpenAPI spec

Generate an API message from this Postman collection item

I need an API message that posts to https://api.example.com/v1/users with body {\"name\":\"Alice\",\"role\":\"admin\"}. Name it New User Request.

Create an API message for https://api.example.com/v1/users. It needs basic authorization with username username and password password.

Create and manage your mobile connections and their capabilities with these actions:

Action

Prompt examples

Create connection

Create a new Appium connection for Sauce Labs

List connections

Show all my mobile connections

Update connection

Update the name of my BrowserStack connection

Delete connection

Remove the mobile connection named LambdaTest

Create capability

Add a tosca:webAppUrl capability to my Sauce Labs connection

Create capability set

Add a capability set for iOS testing to my connection

List capabilities

Show all capabilities for my BrowserStack connection

Update capability

Update the URL value in the tosca:webAppUrl capability

Delete capability or capability set

Delete the iOS capability set

What's next

Now that you're connected to the Tosca Cloud MCP, you can check out the MCP prompting best practices to get the most out of your AI interaction.