Skip to main content
TestDino MCP Server connects AI assistants (Cursor, Claude Desktop) to your workspace. Assistants retrieve real test data, investigate failures, and manage test cases through natural language prompts.

What MCP Enables

CapabilityDescription
Run inspectionQuery runs by branch, environment, time window, author, or commit
Failure analysisPull failure stats, error categories, and raw run JSON
Test case filteringList failed, flaky, slow, or tagged test cases across runs
Debug contextFetch logs, traces, screenshots, and video for any test case
Root cause analysisAnalyze historical execution data to identify failure patterns and causes
Fix recommendationsGet targeted fixes based on past failures and error patterns
Manual test managementSearch, create, update, and organize manual test cases and suites

How It Works

The MCP server runs as a local process started by your AI client. It authenticates with a Personal Access Token and communicates with TestDino APIs on behalf of your assistant.
AI Assistant → MCP Client → TestDino MCP Server → TestDino API
Your assistant sends natural language prompts. The MCP client translates them into tool calls. The server fetches data from TestDino and returns structured results.

Example Prompts

Test run analysis

  • Which are the most flaky test cases from the recent 10 test runs in TestDino?
  • Show me all failed tests from the last run in TestDino.
  • Debug the failing tests from the last run and provide fix suggestions in TestDino.
  • List flaky tests on main from the last 7 days in TestDino.
  • Can you explain the likely root cause of the test case “visual.spec.js” on the development branch in TestDino?

Manual test case management

  • List all critical priority test cases in the checkout suite.
  • Find manual test cases tagged with @auth that are not yet automated.
  • Create a new test case for the password reset flow in the Authentication suite.
  • What test suites exist in project X?

AI Debugging with debug_testcase

The debug_testcase tool aggregates historical execution data for a specific test case across multiple runs.
AnalysisWhat it provides
Root causeAnalyzes past error messages, artifacts, stack traces, and error categories
Failure patternsIdentifies common error categories, messages, and failure locations
Fix recommendationsSuggests fixes based on historical analysis and pattern matching
When source code visibility is limited, treat AI-generated fixes as advice. Validate and adjust manually based on what you observe in the product.

Available Tools

ToolDescription
healthConfirms server is running and token has access
list_testrunsLists test runs with filters (branch, environment, author, time)
get_run_detailsReturns full report for a run or batch of runs
list_testcaseLists test cases across runs with status and tag filters
get_testcase_detailsRetrieves full debug details for a specific test case
debug_testcaseRoot cause analysis with failure patterns and fix recommendations
list_manual_test_casesSearches manual test cases with filters
get_manual_test_caseRetrieves a manual test case with steps and custom fields
create_manual_test_caseCreates a manual test case in a suite
update_manual_test_caseUpdates fields on a manual test case
list_manual_test_suitesLists the suite hierarchy and suite IDs
create_manual_test_suiteCreates a suite (top-level or nested)

Get Started

1

Generate a Personal Access Token

Go to User Settings → Personal Access Tokens in TestDino. Grant access to the projects and modules you want your assistant to query.See Generate API Keys for details.
2

Configure your MCP client

Add TestDino as an MCP server in Cursor or Claude Desktop.See MCP Setup for client-specific instructions.
3

Validate the connection

Ask your assistant to run the health tool and confirm it can see your organisations and projects.
Set up MCP, use tools, and troubleshoot common issues.