Connect to the Tosca Cloud MCP server

With the Model Context Protocol (MCP), AI assistants can access your Tosca Cloud tenant and help you with test automation tasks.

To do that, connect your AI assistant to the Tosca Cloud MCP server.

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.

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

Connect your AI assistant

Copy the MCP configuration from Tosca Cloud:

  1. Go to User menu > Settings > Integrations.

  2. In the AI integrations section, scroll to MCP server and select Set up integration.

  3. Select which workspace you want to connect your AI assistant to. Then, copy the configuration.

Add the copied configuration to your AI assistant. It works as is for Cursor AI and Claude Desktop. For Visual Studio Code and Claude Code, adapt it as shown in the following examples.

To connect Cursor AI or Claude Desktop, add the copied configuration to mcp.json or claude_desktop_config.json.

Source: Cursor documentation (opens in new tab)

Source: Claude Desktop documentation (opens in new tab)

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\"}"
      ]
    }
  }
}

To connect to a different workspace, replace default in the URL with your workspace ID.

To connect Visual Studio Code, open the Command Palette and run MCP: Open User Configuration. Then, add the ToscaCloudMcpServer entry under servers in mcp.json.

Source: Visual Studio Code documentation (opens in new tab)

Copy 
{
  "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\"}"
      ]
    }
  }
}

To connect to a different workspace, replace default in the URL with your workspace ID.

To connect Claude Code, run claude mcp add-json with the command and args values from your copied configuration.

Source: Claude Code documentation (opens in new tab)

Copy 
claude mcp add-json ToscaCloudMcpServer -s user '{
  "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\"}"
  ]
}'

To connect to a different workspace, replace default in the URL with your workspace ID.

After you connect your AI assistant, sign in to Tosca Cloud and complete the 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 blocks MCP servers.

Ask your admin to enable the MCP servers in Copilot policy 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 
{
    "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

Your AI assistant can perform all tasks that the Tosca Cloud interface supports.

For the best results, however, we recommend that you use the Tosca Cloud MCP Server together with the skills we've created. You can get these skills from this Tricentis GitHub repository (opens in new tab).

You can ask the AI assistant directly for a list of available tools. For example, use the following prompt: Give me a list of all available tools.

Alternatively, you can check out the following tables:

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

Find the first 20 API messages created this month

Show playlists with "smoke" in the name

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

Delete folder

Delete the UI tests folder

Rename folder

Rename Regression folder to Regression 2026

Change folder color

Change the color of the UI tests folder to blue

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

Set up a Selenium connection for BrowserStack

List connections

Show all my mobile connections

List the connections in this workspace

Update connection

Update the name of my BrowserStack connection

Rename my BrowserStack connection from BS-old to BS-prod

Delete connection

Remove the mobile connection named LambdaTest

Delete my Appium connection for Sauce Labs

Create capability

Add a tosca:webAppUrl capability to my Sauce Labs connection

Add a deviceName capability to my LambdaTest connection

Create capability set

Add a capability set for iOS testing to my connection

Create a capability set for Android testing on BrowserStack

List capabilities

Show all capabilities for my BrowserStack 1 connection

List the capabilities configured for my Sauce Labs connection

Update capability

Update the URL value in the tosca:webAppUrl capability

Change the platformVersion capability to 15.0

Delete capability or capability set

Delete the iOS capability set

Remove the tosca:webAppUrl capability from my Sauce Labs connection

The Data Integrity MCP actions set is an end-to-end assistant for testing the validity of your table datasets and interpreting the test results.

This is the list of actions available in the Data Integrity MCP:

Action

Description

Prompt examples

Create new Data Integrity connections

The AI creates a Data Integrity connection to the database you specify.

For security purposes, the AI cannot set user passwords or connection strings. The user needs to add those manually, after AI creates the connection in Tosca Cloud.

Additionally, when the AI creates a new Data Integrity connection, it always sets the option Allow AI queries to off. When the option Allow AI queries is off, the AI can't retrieve metadata from that connection. This means that it can't create or fix SQL statements in Tosca Cloud for that connection. If you want to manage these SQL statements through prompts, you need to manually turn on Allow AI queries for this connection.

Note: We recommend that you use user credentials with read-only access to your database. Especially when working with connections with that Allow AI queries.

Create a DI connection to my Azure database with the address tcp:myserver.database.windows.net,1433.

Create a new SQL query

The AI creates an SQL query that retrieves the data you specify from a Data Integrity connection with the setting Allow AI queries selected. The AI can read instructions both in natural language and in pseudo-code.

For this test, include only the customer names and last order dates for shipped orders in 2026.

If order.status = 'SHIPPED' AND YEAR in last.order.on = 2026 THEN SELECT name and last.order.on.

Validate an existing SQL query

The AI verifies if an SQL query in Tosca Cloud fetches the data you want from a Data Integrity connection with the setting Allow AI queries selected.

Does the query to my Azure database in the test "Data comparison 1" fetch the shipped orders from the last three months?

Transfer data from an SAP database to the caching database

The AI creates a test step with the Load Data into Caching Database from Customization Module and the SAP Custom Data Reader. That test step creates a table in the caching database with the data it fetches from the SAP database, according to your specifications.

I want to check the data in the Orders table in the sap-server.acme.com, instance number 01 and client 101. Can you create a test for that? 

Check specific table cells

The AI creates a test case using one or more DI DB Expert Modules according to your specifications. It can use an existing connection to access the table you want to check, or create a new one if an applicable one doesn't exist.

Confirm that the last cell in the first column of the table Orders in my SAP database has the value "Shipped".

Confirm that the cells in the seventh row in the columns Order.price and base.price in the table Orders in my Azure database are less than 2000.

Check the validity of a table dataset

The AI creates a test using the Complete Row by Row Comparison Module.

This tool can use your input to set up the following assets and test steps:

  • Create a Data Integrity connection and/or data transfer from SAP to access the data for the test.

  • Create an SQL query and add it to the test.

  • Set up the column mapping.

  • Set DateTime tolerances.

  • Recommend and set a row key.

This tool can also set up tests using a CSV mapping file from a data governance tool, for example: Collibra. This file describes the relationship between the two datasets you want to compare. This way, you only need to tell the AI what you want to check after you provide the file.

Check if the customer name and date of last order columns in the Orders tables in my Azure and SAP databases match.

Validate existing tests

The AI confirms if an existing test works as you describe.

I want to check if the columns with the customer names in the Orders tables in my Oracle and Snowflake databases match. But the target column is named "Customer" and the source column is named 'names'. Is the test 'Names Check' designed match the correct columns?

Update existing tests

The AI makes any change that you ask in existing Data Integrity test assets.

In the "Names Check" test, change the value of the row key to the order.code column.

Discuss test results

The AI explains the results of dataset comparison to you. It groups errors according to their type, for example: unmapped columns, DateTime mismatch, or actual data differences, and presents them to you in conversation. This way, it can let you know if it was an incorrect test configuration that caused the errors.

Check how many of the mismatches in the time column, are differences of less than a second.

Fix tests using test results

The AI suggests and apply fixes to dataset comparison tests that have incorrect configurations, after checking their test results.

AI response: Your source column uses European date format (DD.MM.YYYY) while the target order.dates column uses US format (MM/DD/YYYY) — that mismatch is what's driving all the comparison failures. I can resolve this by configuring the DateTime tolerance settings in your test. Want me to go ahead?

Note that you don't need to describe each step in test creation through prompts. A straightforward prompt will start the process. For example:

Check that the customer names and last order dates in the Orders tables in my Azure and Snowflake databases are the same.

The AI will then ask you follow-up questions for any further details it needs.

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.