- METRICS
- TRIAGE
- REPORTS
- HUMAN
Short answer
How do I track pass and fail rates in my automation runs?
Your AI queries LambdaTest to pull build metadata and session statuses. It then calculates pass and fail rates to show you exactly where your builds are failing. You get a clear view of your test stability without manual log digging.
Where your data lands.
The outcomes of your queries.
The AI organizes your LambdaTest data into these specific outcomes.
METRICS
Build health trends
The AI aggregates pass and fail rates from recent runs. You get a high-level view of whether your suite is getting more or less stable.
TRIAGE
Failure identification
The AI identifies specific failed sessions. It pinpoints exactly which tests are breaking so you don't have to hunt through logs.
REPORTS
Summary snapshots
The AI generates concise summaries of build metadata. You receive a clean breakdown of build duration and status.
HUMAN
Manual debugging
The AI flags the specific session IDs that need your attention. You take over to inspect the actual video or screenshots in LambdaTest.
The workflow
What your AI does when the data arrives.
The AI acts as a bridge between your test results and your chat interface.
Fetch build history
The AI pulls a list of recent automation runs to establish a baseline for your health checks.
list_automation_buildsInspect build specifics
It looks into the details of a specific run to find the exact status and metadata.
get_build_detailsAnalyze session results
The AI examines individual test sessions to separate passing tests from failing ones.
list_test_sessionsReport health status
The AI combines the session data and build metadata to give you a final pass/fail percentage.
list_test_sessions
Try it
Copy these to start.
Use these prompts to begin monitoring your runs.
Starting points
Swap out the bracketed text with your actual build IDs or project names.
LambdaTest Connector
You're all set. Choose your MCP client and follow the setup instructions.
https://edge.vinkius.com/vk_preview_4JlG89G0mrRFQv1NEMOe3quOG8MUgnbaUJbJ9Hdc/mcpClaude Desktop
Follow the steps below to connect in seconds.
- 1In Claude Desktop, open Settings → Connectors.
- 2Click “Add custom connector” and paste the connector link above as the remote MCP server URL.
- 3Click Add and start a new chat — LambdaTest capabilities are ready to use.
{
"mcpServers": {
"lambdatest-mcp": {
"url": "https://edge.vinkius.com/vk_preview_4JlG89G0mrRFQv1NEMOe3quOG8MUgnbaUJbJ9Hdc/mcp"
}
}
}What is the pass rate for my last build in the 'Mobile-Regression' suite?
List the failed sessions from my most recent automation build.
Check the status of build ID 12345 and tell me why it failed.
Summarize the health of my 'Web-Smoke-Test' runs from the last 24 hours.
Claude
ChatGPT
Cursor
VS Code
Windsurf
Claude Code
JetBrains
Cline
Start here
Connect LambdaTest once, then ask.
Follow the link to authorize the connection. Your credentials stay encrypted, and you can immediately start asking your AI about your test data.
Connect LambdaTest to your AIFAQ
Common questions
- 01
Can the AI fix my failing tests?
No. The AI can identify which tests failed and provide the metadata, but you must manually fix the code.
- 02
Can the AI delete old builds in LambdaTest?
No. This MCP only has permissions to read build and session data. It cannot modify or delete anything in your LambdaTest account.
- 03
How does the AI know which builds are recent?
It uses the build metadata provided by the list_automation_builds tool to see timestamps and run history.
- 04
Does the AI see my test videos?
No. The AI reads the text-based metadata and session statuses. It cannot watch or process video files.
- 05
Can I use this with any AI client?
Yes, as long as the client supports the Model Context Protocol (MCP).
More questions about LambdaTest? The Connector page answers them. See everything the LambdaTest Connector can do
Connect LambdaTest to Claude, Cursor, ChatGPT & more
