Discovery & generation

Discovery & generation

This page is generated from the live QualityMax MCP registry. Examples use placeholders; replace them with values for your workspace.

check_ai_crawl_status

Purpose

Check the status of an AI crawl job. Use this to see if a crawl has completed and inform the user when tests are ready.

Parameters

Parameter	Type	Required	Description
crawl_id	string	Yes	The crawl job ID to check status for

Return shape

The live registry does not declare a response schema. Expect a tool-specific JSON result and handle success, error, and result fields defensively.

Worked example

{
  "arguments": {
    "crawl_id": "your-crawl-id"
  },
  "tool": "check_ai_crawl_status"
}

generate_area_plan

Purpose

Run deep gap analysis on a repository to discover and map testing areas.

Parameters

Parameter	Type	Required	Description
repo_id	string	Yes	Repository ID to analyze

Return shape

The live registry does not declare a response schema. Expect a tool-specific JSON result and handle success, error, and result fields defensively.

Worked example

{
  "arguments": {
    "repo_id": "your-repo-id"
  },
  "tool": "generate_area_plan"
}

generate_code_for_test_case

Purpose

Generate automation test code for a specific test case. Call get_test_capabilities first and use its recommendation unless evidence favors an override; then execute the result and continue its autonomous QA loop. Supports Playwright, pytest, Cypress, Selenium, Vitest, Jest, Kotlin, Scala, Go (go test), and Rust (cargo test). When framework is omitted, the framework is auto-resolved from project settings, linked-repository language detection, and the test category.

For a test case in a Native Mobile project, pass framework: "appium" together with platform (‘android’ or ‘ios’). That is a different lane: the test case’s steps are compiled deterministically into a managed native script (no AI generation, no coding-seat job, so it answers inline), and the response is compact metadata rather than code. Run the resulting script_id with run_tests — not run_native_test, which is for Go/Rust/Jest only. Generic frameworks will produce browser-oriented code for a native case.

Parameters

Parameter	Type	Required	Description
test_case_id	integer	Yes	Test case ID to generate code for
framework	string	No	Optional framework override. One of: playwright, pytest, cypress, selenium, jest, vitest, kotlin, scala, go, rust, appium. Use ‘appium’ for a native mobile test case, and pass platform with it. When omitted, the framework is auto-detected from the linked repository or test category — auto-detection never selects appium.
platform	string	No	Native mobile platform for framework: "appium". Required when the project has both an Android and an iOS app connected; otherwise it defaults to the single connected platform. Rejected for every other framework.
generation_service	string	No	Code-generation service; auto uses the project setting

Return shape

The live registry does not declare a response schema. Expect a tool-specific JSON result and handle success, error, and result fields defensively.

Worked example

{
  "arguments": {
    "test_case_id": 1
  },
  "tool": "generate_code_for_test_case"
}

generate_gap_tests

Purpose

Generate test cases to fill coverage gaps found by analyze_coverage. Analyzes the repository’s deep-scan results and generates E2E, smoke, integration, and security test cases.

Parameters

Parameter	Type	Required	Description
repo_id	string	Yes	Repository ID to generate gap tests for
max_tests	integer	No	Maximum number of tests to generate per category (default: 5)

Return shape

The live registry does not declare a response schema. Expect a tool-specific JSON result and handle success, error, and result fields defensively.

Worked example

{
  "arguments": {
    "repo_id": "your-repo-id"
  },
  "tool": "generate_gap_tests"
}

generate_tests

Purpose

Generate Playwright tests for a specific feature or component

Parameters

Parameter	Type	Required	Description
repo_id	string	Yes	Repository ID to generate tests for
feature_description	string	Yes	Description of the feature to test
test_type	string	No	Type of tests to generate
selectors	array	No	Specific selectors to target

Return shape

The live registry does not declare a response schema. Expect a tool-specific JSON result and handle success, error, and result fields defensively.

Worked example

{
  "arguments": {
    "feature_description": "your-feature-description",
    "repo_id": "your-repo-id"
  },
  "tool": "generate_tests"
}

generate_tests_for_areas

Purpose

Generate test cases for specific discovered test areas.

Parameters

Parameter	Type	Required	Description
repo_id	string	Yes	Repository ID
area_ids	array	Yes	List of TestArea IDs to generate tests for
categories	array	No	Optional specific categories to generate (e.g. e2e, a11y, ux). If omitted, uses recommended categories.
max_tests_per_area	integer	No	Max tests to generate per area

Return shape

The live registry does not declare a response schema. Expect a tool-specific JSON result and handle success, error, and result fields defensively.

Worked example

{
  "arguments": {
    "area_ids": [],
    "repo_id": "your-repo-id"
  },
  "tool": "generate_tests_for_areas"
}

get_ai_crawl_results

Purpose

Get the results of a completed AI crawl job including generated test scripts, test cases, and flow memory.

Parameters

Parameter	Type	Required	Description
crawl_id	string	Yes	The crawl job ID to get results for

Return shape

The live registry does not declare a response schema. Expect a tool-specific JSON result and handle success, error, and result fields defensively.

Worked example

{
  "arguments": {
    "crawl_id": "your-crawl-id"
  },
  "tool": "get_ai_crawl_results"
}

import_document_and_crawl

Purpose

Complete workflow: Import document/text, create test cases, generate virtual test plan for approval, then initiate AI crawl. IMPORTANT: This tool will first generate a virtual test plan that MUST be approved by the user before proceeding. You must present the plan to the user, wait for their approval, then call this tool again with the approved_virtual_test_plan parameter to proceed with the crawl.

Parameters

Parameter	Type	Required	Description
project_id	integer	Yes	Project ID to import into
text_content	string	Yes	Document text content to import (required if not using file_url)
source_name	string	No	Optional name for the document source
url	string	No	Project URL for AI crawl (will use project.main_url if not provided)
test_case_id	integer	No	Test case ID to crawl from (optional - will list test cases if not provided)
depth	integer	No	Crawl depth
pages_limit	integer	No	Maximum pages to crawl
test_type	string	No	Type of test to generate
framework	string	No	Test framework
enable_giskard_validation	boolean	No	Enable Giskard validation
approved_virtual_test_plan	object	No	Approved virtual test plan object (required for second call after user approves the plan). Include the full virtual_test_plan object from the first call response.

Return shape

The live registry does not declare a response schema. Expect a tool-specific JSON result and handle success, error, and result fields defensively.

Worked example

{
  "arguments": {
    "project_id": 1,
    "text_content": "your-text-content"
  },
  "tool": "import_document_and_crawl"
}

start_ai_crawl

Purpose

Start an AI crawl job for a project (requires project.main_url unless url is provided). For a Native Mobile project this runs mobile discovery against the connected app instead of a browser crawl — no URL is needed, custom_instructions is required, and the crawl starts immediately rather than returning a plan to approve. Use it to discover real on-device element selectors when a native test case has steps the mobile flow compiler cannot resolve.

Parameters

Parameter	Type	Required	Description
project_id	integer	Yes	No description supplied.
url	string	No	No description supplied.
depth	integer	No	No description supplied.
pages_limit	integer	No	No description supplied.
test_type	string	No	No description supplied.
framework	string	No	No description supplied.
enable_giskard_validation	boolean	No	No description supplied.
custom_instructions	string	No	What to explore. Required for a native_mobile crawl, which produces nothing without it.
crawl_mode	string	No	Which pipeline to run. Defaults to ‘native_mobile’ for a Native Mobile project and ‘web’ otherwise, so this rarely needs to be set explicitly.
platform	string	No	Native app platform. Inferred when exactly one app is connected; required when the project has both Android and iOS apps.

Return shape

The live registry does not declare a response schema. Expect a tool-specific JSON result and handle success, error, and result fields defensively.

Worked example

{
  "arguments": {
    "project_id": 1
  },
  "tool": "start_ai_crawl"
}

start_ai_crawl_from_test_case

Purpose

Start an AI crawl job using an existing test case as instructions. IMPORTANT: This tool will first generate a virtual test plan that MUST be approved by the user before proceeding. You must present the plan to the user, wait for their approval, then call this tool again with the approved_virtual_test_plan parameter to proceed with the crawl. A test case in a Native Mobile project is the exception: it runs mobile discovery against the connected app, needs no URL, and starts immediately with no plan to approve — the mobile pipeline is never handed one.

Parameters

Parameter	Type	Required	Description
test_case_id	integer	Yes	No description supplied.
url	string	No	No description supplied.
depth	integer	No	No description supplied.
pages_limit	integer	No	No description supplied.
test_type	string	No	No description supplied.
framework	string	No	No description supplied.
enable_giskard_validation	boolean	No	No description supplied.
approved_virtual_test_plan	object	No	Approved virtual test plan object (required for second call after user approves the plan). Include the full virtual_test_plan object from the first call response.
crawl_mode	string	No	Which pipeline to run. Defaults to ‘native_mobile’ for a Native Mobile project and ‘web’ otherwise, so this rarely needs to be set explicitly.
platform	string	No	Native app platform. Inferred when exactly one app is connected; required when the project has both Android and iOS apps.

Return shape

The live registry does not declare a response schema. Expect a tool-specific JSON result and handle success, error, and result fields defensively.

Worked example

{
  "arguments": {
    "test_case_id": 1
  },
  "tool": "start_ai_crawl_from_test_case"
}