Kiwi
Kiwi

Kiwi for TestMu AI

Have the agent on a Kiwi step triage failed tests and check visual and accessibility results in TestMu AI, formerly LambdaTest, through its MCP server.

  • Your agent works in TestMu AI through its own connection. Kiwi does not call TestMu AI and never holds its credentials.
  • A workflow skill can list TestMu AI among the tools it requires. When you supply your agent's available tools to a skill check and TestMu AI is not among them, the check reports SK15-UNSUPPORTED-TOOL.
  • A project Admin can add links to TestMu AI, 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 TestMu AI connection, with report_configuration.
  • The agent submits links to its work in TestMu AI as the step's outputs. People review them, and sign-off stays with the people your workflow names.

What your agent can do in TestMu AI

  • Pull a failed test's details, command logs, network logs and console errors together to find the root cause.
  • Generate HyperExecute YAML and test runner commands, and monitor HyperExecute jobs.
  • Explain the pixel, layout and DOM changes in a SmartUI visual comparison.
  • Run WCAG accessibility audits on public URLs and tunneled apps.
  • Generate test cases, build test runs and record results in bulk in Test Manager.

Set up

  1. Connect your agent to Kiwi

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

    Coding agentsQuickstart

  2. Connect your agent to TestMu AI

    Add the TestMu AI MCP server to your agent with this URL. The credentials stay with your agent.

    https://mcp.lambdatest.com/mcp

    TestMu AI documentation

  3. Example skill

    Publish instructions like these as a workflow skill that lists TestMu AI among its required tools.

    Start from the test IDs of the failed tests named in the assignment.
Pull each test's command, network and console logs from TestMu AI.
Fix the cause in the tests or the code and note the test it came from.
Submit the test links and a note per failure as the step's outputs.
If the logs are missing, stop and report a blocker to the step owner;
the assigned reviewer decides on failures that remain.
Get startedRead the setup guide