Skip to content

Supported Tools

The TestGen MCP server exposes the prompts, tools, and resources listed below.

For setup instructions, see Set up the MCP Server. For example questions to ask an assistant, see MCP Server.

Prompts

Prompts are pre-built workflows you can invoke directly through your AI client — typically as a slash command (for example, /testgen:table_health in Claude Code) or from a quick-action menu. They orchestrate several tool calls behind the scenes for common investigations. Exact UX varies by client.

  • compare_runs — Compare the most recent test run against the previous run to identify regressions and improvements.
  • health_check — Run a data quality health check across all projects and test suites.
  • hygiene_triage — Guided hygiene issue triage workflow — review hygiene issues and decide what to do.
  • investigate_failures — Investigate test failures to identify root causes and patterns.
  • profiling_overview — Explore the profiling results for a table group — understand data shapes, types, null rates, and hygiene issues.
  • table_health — Assess the data quality health of a specific table across all test suites.

Tools

Tools are operations the assistant calls during a conversation, picked based on what you ask.

Discover what TestGen knows about

  • get_data_inventory — Get a structural inventory of all projects, connections, table groups, and test suites accessible to the authenticated user.
  • get_test_type — Get detailed information about a specific test type.
  • list_projects — List all projects the authenticated user has access to.
  • list_tables — List tables in a table group.
  • list_test_suites — List all test suites for a project with their latest run statistics.

Investigate quality issues

  • bulk_update_tests — Enable or disable tests in a suite in bulk.
  • compare_test_runs — Compare two test runs and report regressions, improvements, persistent failures, and added/removed tests.
  • create_test — Create a test in a test suite.
  • create_test_note — Attach a note to a test definition.
  • delete_test_note — Delete a test note. Only the note's author can delete it.
  • get_failure_summary — Summarize test failures (Failed and Warning) grouped by test type, table, or column.
  • get_failure_trend — Time-series of test result counts by time bucket — use this to see whether failures are trending up or down.
  • get_source_data — Look up rows from the connected database that match or violate a test definition's criteria.
  • get_source_data_query — Get the SQL query that would be used to look up source data for a test definition, without executing it.
  • get_test — Get full details of a test definition, including configuration, parameters, and last result.
  • get_test_run — Get a single test run with status, timing, result counts, and testing score. Returns the run regardless of state — including queued and in-progress runs without complete results yet.
  • list_test_notes — List notes attached to a test definition, newest first.
  • list_test_result_history — Get the historical results of a specific test definition across runs, showing how measure and status changed over time.
  • list_test_results — List individual test results for a test run, with optional filters.
  • list_test_runs — List test runs across a project, including queued and in-progress runs. Ordered by submission time descending. Excludes monitor suites.
  • list_test_types — List available test types with optional filtering.
  • list_tests — List test definitions in a test suite.
  • search_test_results — Search test results across multiple runs with flexible filters.
  • update_test — Update fields on an existing test. Atomic — no partial save.
  • update_test_note — Replace the body of a test note. Only the note's author can update it.
  • validate_custom_test — Dry-run a custom test SQL query against the test suite's parent connection.

Browse profiling results

  • compare_profiling_runs — Compare two profiling runs on the same table group and report metric changes for shared columns plus hygiene issue churn.
  • get_column_frequent_values — Get the top frequent values for one column from its profile run, with row counts and percentages.
  • get_column_patterns — Get the top character patterns for one string column from its profile run.
  • get_column_profile_detail — Get the type-specific value distribution and statistics for one column from its profiling run.
  • get_hygiene_issue — Get full details of a specific hygiene issue.
  • get_profiling_run — Get a single profiling run with status, timing, totals, and per-table breakdown. Returns the run regardless of state — including queued and in-progress runs without complete results yet. The per-table breakdown is only available after the run completes.
  • get_profiling_trends — Show a time series of caller-named profiling metrics across recent completed runs of a table group.
  • get_schema_history — Show a per-run timeline of structural changes across recent profiling runs — tables and columns added or dropped, type changes, and record-count deltas per table.
  • get_table — Get an overview of a table with profiling highlights: structural metadata, column list, quality scores, and hygiene issue count from the latest profiling run.
  • list_column_profiles — List per-column profile headers across a table group, with optional profile-predicate filters.
  • list_hygiene_issues — List hygiene issues for a profiling run.
  • list_profiling_runs — List profiling run history for a table group, including queued, in-progress, and failed runs. Ordered by submission time descending.
  • list_profiling_summaries — List aggregated profiling health summaries for a table group or across a project — quality scores, hygiene issue counts, record counts, last profiled date.
  • search_columns — Search columns by name across one or many projects (bare tokens auto-wrap as %token%; explicit % honored as a wildcard).
  • search_hygiene_issues — Search hygiene issues across profiling runs and table groups.
  • update_hygiene_issue — Update the disposition of a hygiene issue (confirm, dismiss, or mute).

Trigger profiling, tests, and test generation

  • cancel_profiling_run — Request cancellation of a queued or running profiling run.
  • cancel_test_run — Request cancellation of a queued or running test run.
  • create_profiling_schedule — Create a recurring profiling schedule for a table group.
  • create_test_run_schedule — Create a recurring test-run schedule for a test suite.
  • delete_schedule — Delete a schedule. Past executions remain accessible via list_test_runs / list_profiling_runs.
  • generate_tests — Submit a test-generation job for a test suite. Auto-creates test definitions from the latest profiling results for the table group; locked and manually created test definitions are preserved. Returns immediately with a job_execution_id.
  • get_schedule — Get full details for a schedule, including the last five execution attempts.
  • list_schedules — List schedules for a project — profiling and test run schedules.
  • run_profiling — Submit a profiling run for a table group. Returns immediately with a job_execution_id; use list_profiling_summaries to track status.
  • run_tests — Submit a test run for a test suite. Returns immediately with a job_execution_id; use list_test_runs to track status.
  • update_schedule — Update a schedule's cron, timezone, or active state. Atomic — no partial save.

Track data quality scores

  • create_scorecard — Create a scorecard in a project.
  • delete_scorecard — Delete a scorecard.
  • get_quality_scores — Quality-score rollup with optional grouping and filtering.
  • get_scorecard — Get a scorecard with its current scores and per-category breakdown.
  • list_scorecards — List the scorecards defined in a project.
  • update_scorecard — Update fields on an existing scorecard. Pass only the fields to change.

Manage TestGen configuration

  • create_notification — Create an email notification for a test-run, profiling-run, or score-drop event.
  • delete_notification — Delete an email notification.
  • get_notification — Get full details of an email notification: event type, trigger or thresholds, scope (project, test suite, table group, or scorecard), and recipients.
  • list_notifications — List notifications configured across projects, or scoped to a parent entity.
  • update_notification — Update fields on an existing email notification. Pass only the fields to change.

Resources

Resources are static reference documents that AI clients can fetch by URI.

  • testgen://column-profile-fields — Reference for column-profile fields by general_type, with PII redaction notes.
  • testgen://glossary — Glossary of TestGen concepts, entity hierarchy, result statuses, and quality dimensions.
  • testgen://hygiene-issue-types — Reference table of all hygiene issue types with their data quality dimensions, descriptions, and suggested actions.
  • testgen://test-types — Reference table of all test types with their descriptions and data quality dimensions.