Kiwi

Kiwi for BrowserStack Test Management

Have the agent on a Kiwi step write test cases, create test runs and log results in BrowserStack Test Management through BrowserStack's MCP server.

  • Your agent works in BrowserStack Test Management through its own connection. Kiwi does not call BrowserStack Test Management and never holds its credentials.
  • A workflow skill can list BrowserStack Test Management among the tools it requires. When you supply your agent's available tools to a skill check and BrowserStack Test Management is not among them, the check reports SK15-UNSUPPORTED-TOOL.
  • A project Admin can add links to BrowserStack Test Management, with notes, under Connections and bind them to the steps that use them. The agent reads them with list_connections.
  • The agent can report the tools and plugins it ran with, including its BrowserStack Test Management connection, with report_configuration.
  • The agent submits links to its work in BrowserStack Test Management as the step's outputs. People review them, and sign-off stays with the people your workflow names.

What your agent can do in BrowserStack Test Management

  • Create a project or folder for the cases that cover a feature.
  • Create and update test cases with steps, expected results, priority, tags and custom fields.
  • Create a test run from chosen test cases, with configurations, a test plan, an assignee and linked requirements.
  • Log a result for a test in a run, with a status, notes, attachments and linked defects.

Set up

  1. Connect your agent to Kiwi

    Add Kiwi's hosted MCP server, https://kiwiflow.io/mcp, to your coding agent.

  2. Connect your agent to BrowserStack Test Management

    Add the BrowserStack Test Management MCP server to your agent with this URL. The credentials stay with your agent.

    https://mcp.browserstack.com/mcp
  3. Example skill

    Publish instructions like these as a workflow skill that lists BrowserStack Test Management among its required tools.

    Start from the feature and the Test Management project in the assignment.
    Write test cases for the feature with steps and expected results.
    Create a test run with those cases and log a result for each one.
    Submit the test run link and the failed case IDs as the step's outputs.
    If a write is refused, stop and report a blocker to the step owner; the
    assigned reviewer reads the run in BrowserStack.