Test management

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

`check_ai_review_status`

Purpose

Check a background AI review started by ai_review and return its result when complete.

Parameters

Parameter	Type	Required	Description
`job_id`	`string`	Yes	AI review job ID returned by ai_review

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": {
    "job_id": "your-job-id"
  },
  "tool": "check_ai_review_status"
}

`check_generation_status`

Purpose

Check a background code-generation job started by generate_code_for_test_case. Worker-backed deployments return a job_id because generation can take minutes. Poll about every 30s until ‘completed’, ‘failed’, or ‘timed_out’. Personal Codex / Claude Code seats run one job at a time, so do not queue seat jobs in parallel.

Parameters

Parameter	Type	Required	Description
`job_id`	`string`	Yes	The job_id returned by generate_code_for_test_case

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": {
    "job_id": "your-job-id"
  },
  "tool": "check_generation_status"
}

`create_deploy_integration`

Purpose

Create a deploy-provider webhook integration for a project. Auto-generates a webhook URL and secret. Returns the full secret (only shown once), the URL, and provider-specific setup instructions. One integration per provider per project.

Parameters

Parameter	Type	Required	Description
`project_id`	`integer`	Yes	The QM project ID.
`provider`	`string`	No	Deploy provider (default: vercel).

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": "create_deploy_integration"
}

`create_test_case`

Purpose

Create a test case in a project. If no steps are provided, detailed steps are auto-generated from the title/description (disable with auto_generate_steps=false).

Parameters

Parameter	Type	Required	Description
`project_id`	`integer`	Yes	No description supplied.
`title`	`string`	Yes	No description supplied.
`description`	`string`	No	No description supplied.
`detailed_instructions`	`string`	No	No description supplied.
`steps`	`array`	No	Explicit test steps; when omitted, steps are auto-generated
`auto_generate_steps`	`boolean`	No	Auto-generate Detailed Steps via AI when no steps are provided
`priority`	`value`	No	Priority: 1-5 (integer) or critical/high/medium/low (string)
`category`	`string`	No	No description supplied.
`tags`	`array`	No	No description supplied.

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,
    "title": "your-title"
  },
  "tool": "create_test_case"
}

`delete_deploy_integration`

Purpose

Delete a deploy-provider webhook integration. The provider must be told to stop sending events afterwards — this only removes the QualityMax side.

Parameters

Parameter	Type	Required	Description
`project_id`	`integer`	Yes	The QM project ID.
`integration_id`	`integer`	Yes	The integration ID to delete.

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": {
    "integration_id": 1,
    "project_id": 1
  },
  "tool": "delete_deploy_integration"
}

`delete_project`

Purpose

Delete a project. Requires ownership. This will also delete all associated test cases, scripts, and executions.

Parameters

Parameter	Type	Required	Description
`project_id`	`integer`	Yes	Project ID to delete

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": "delete_project"
}

`delete_script`

Purpose

Delete an automation script. Requires ownership of the parent project.

Parameters

Parameter	Type	Required	Description
`script_id`	`integer`	Yes	Automation script ID to delete

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": {
    "script_id": 1
  },
  "tool": "delete_script"
}

`delete_test_case`

Purpose

Delete a test case. Requires ownership of the parent project.

Parameters

Parameter	Type	Required	Description
`test_case_id`	`integer`	Yes	Test case ID to delete

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": "delete_test_case"
}

`enhance_test_case`

Purpose

Enhance a test case with AI — adds more detailed steps, verification points, and improves the description.

Parameters

Parameter	Type	Required	Description
`test_case_id`	`integer`	Yes	Test case ID to enhance

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": "enhance_test_case"
}

`get_discovery_graph`

Purpose

Return the repository’s evidence-grounded discovery graph: a lineage of repository → evidence → test areas → test cases → automation scripts, with grounding status and confidence per node. Use to audit test coverage lineage.

Parameters

Parameter	Type	Required	Description
`repo_id`	`string`	Yes	Repository ID

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": "get_discovery_graph"
}

`get_project_agent_instructions`

Purpose

Get project-specific instructions for testing changing preview/staging URLs using QualityMax MCP. Returns a copyable prompt, installable SKILL.md, revision, and allowlisted saved project facts. Read-only; does not select a deployment, change settings, or prove script portability/access. Use run_tests.base_url for the exact deployment after checking hardcoded URLs.

Parameters

Parameter	Type	Required	Description
`project_id`	`integer`	Yes	Existing project ID
`workflow`	`string`	No	Agent workflow to retrieve

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": "get_project_agent_instructions"
}

`get_project_memory`

Purpose

Return compact durable memory from prior MCP agent negotiations, project learnings, and verified test runs. Call this before generating or repairing tests for an existing project; then call get_script only for the most relevant verified script to keep context and cost low.

Parameters

Parameter	Type	Required	Description
`project_id`	`integer`	Yes	Project whose memory should be recalled
`test_case_id`	`integer`	No	Optional test case filter for the most relevant verified runs
`limit`	`integer`	No	Maximum verified scripts and MCP sessions to return (max 20). Additive reuse fields include grounded learnings, ranked session sequences, graph traversal, and provenance.
`query`	`string`	No	Optional bounded task query used to recall relevant semantic learnings and agent episodes.
`intent`	`string`	No	Optional recall intent. Valid only with query.
`downstream_reuse`	`boolean`	No	Optional client-reported outcome for a previously recalled memory; used only for aggregate telemetry.

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": "get_project_memory"
}

`get_project_summary`

Purpose

Get a summary of a project including counts of test cases, scripts, and executions. Use this when the user asks ‘what’s in my project?’ or ‘show me project stats’.

Parameters

Parameter	Type	Required	Description
`project_id`	`integer`	Yes	Project ID to get summary for
`fields`	`array`	No	Optional subset to return: last_activity, project, statistics. Omit for everything.

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": "get_project_summary"
}

`get_repository`

Purpose

Get repository details and stored analysis

Parameters

Parameter	Type	Required	Description
`repo_id`	`integer`	Yes	No description supplied.

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": 1
  },
  "tool": "get_repository"
}

`get_script`

Purpose

Get an automation script’s details including the generated Playwright/Cypress test code. Pass if_version_matches with the version from a previous read to get a cheap not_modified answer, and fields to fetch only what you need.

Parameters

Parameter	Type	Required	Description
`script_id`	`integer`	Yes	Automation script ID
`fields`	`array`	No	Optional subset of script fields to return: code, created_at, framework, id, name, project_id, test_case_id, version. Omit for the full record.
`if_version_matches`	`string`	No	Version from a previous get_script/update_script. If the code is unchanged, the tool returns `not_modified` instead of the code.

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": {
    "script_id": 1
  },
  "tool": "get_script"
}

`get_test_capabilities`

Purpose

Start here before generating or running tests. Returns the frameworks, code-generation services, execution services, best-fit recommendation, and an autonomous QA loop. For a testing request, follow that loop proactively, strongly suggest the next highest-risk gap, and continue without waiting between safe steps until its stop conditions are met. Includes discovery for project-specific preview-testing agent instructions.

Parameters

Parameter	Type	Required	Description
`project_id`	`integer`	Yes	Project to plan and test
`test_case_id`	`integer`	No	Optional test case used to refine the framework recommendation

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": "get_test_capabilities"
}

`get_test_case`

Purpose

Get detailed information about a specific test case including its description, steps, and related automation scripts. Pass if_version_matches to skip the body when nothing changed, and fields to fetch only what you need.

Parameters

Parameter	Type	Required	Description
`test_case_id`	`integer`	Yes	Test case ID to get details for
`fields`	`array`	No	Optional subset of test-case fields to return: category, description, detailed_instructions, id, preconditions, priority, project_id, status, steps, tags, title, version. Omit for the full record.
`if_version_matches`	`string`	No	Version from a previous get_test_case. If the case is unchanged, the tool returns `not_modified` instead of the full record.

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": "get_test_case"
}

`import_from_testrail`

Purpose

Import test cases from TestRail into a project (requires saved TestRail credentials)

Parameters

Parameter	Type	Required	Description
`project_id`	`integer`	Yes	No description supplied.
`testrail_project_id`	`integer`	Yes	No description supplied.
`testrail_suite_id`	`integer`	No	No description supplied.

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,
    "testrail_project_id": 1
  },
  "tool": "import_from_testrail"
}

`import_repository`

Purpose

Import and analyze a GitHub repository for testing. Creates a default project if none specified.

Parameters

Parameter	Type	Required	Description
`repo_url`	`string`	Yes	GitHub repository URL (e.g., https://github.com/user/repo)
`branch`	`string`	No	Branch to analyze (defaults to main)
`project_id`	`integer`	No	Existing project ID to associate repository with
`create_project`	`boolean`	No	Create a new project for this repository
`project_name`	`string`	No	Name for new project (required if create_project is true)
`training_consent`	`string`	No	Whether repository code can be used for training (default: opt_out)

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_url": "https://example.com"
  },
  "tool": "import_repository"
}

`import_test_cases_from_document`

Purpose

Import test cases from document text content. The AI will analyze the text and extract test cases automatically.

Parameters

Parameter	Type	Required	Description
`project_id`	`integer`	Yes	No description supplied.
`text_content`	`string`	Yes	Document text content to extract test cases from
`source_name`	`string`	No	Optional name for the document source (e.g., ‘Requirements Document’, ‘Test Plan v2.0’)

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_test_cases_from_document"
}

`list_ai_crawl_jobs`

Purpose

List AI crawl jobs for a project, ordered by most recent first.

Parameters

Parameter	Type	Required	Description
`project_id`	`integer`	Yes	Project ID to list crawl jobs for
`limit`	`integer`	No	Maximum number of jobs to return (default: 20)

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": "list_ai_crawl_jobs"
}

`list_auth_profiles`

Purpose

List secret-free authentication profile metadata for a project. Use the returned profile id in run_tests or apply_patch_and_run; never ask the user to paste credentials into a prompt or script.

Parameters

Parameter	Type	Required	Description
`project_id`	`integer`	Yes	Project ID

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": "list_auth_profiles"
}

`list_deploy_integrations`

Purpose

List deploy-provider webhooks (Vercel, Netlify, manual) configured for a project. Read-only. The webhook_secret is masked in the response.

Parameters

Parameter	Type	Required	Description
`project_id`	`integer`	Yes	The QM project ID.

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": "list_deploy_integrations"
}

`list_projects`

Purpose

List projects for the current user, including each project’s vanity URL slug and project type (web or native_mobile). ALWAYS call this before creating a new project to check if a similar project already exists.

Parameters

Parameter	Type	Required	Description
`limit`	`integer`	No	No description supplied.
`offset`	`integer`	No	No description supplied.

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": {},
  "tool": "list_projects"
}

`list_repositories`

Purpose

List repositories for a project

Parameters

Parameter	Type	Required	Description
`project_id`	`integer`	Yes	No description supplied.
`limit`	`integer`	No	No description supplied.
`offset`	`integer`	No	No description supplied.

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": "list_repositories"
}

`list_scripts`

Purpose

List automation scripts for a project or test case. Returns script names and IDs (use get_script to view the code).

Parameters

Parameter	Type	Required	Description
`project_id`	`integer`	Yes	Project ID to list scripts for
`test_case_id`	`integer`	No	Optional: filter scripts by test case ID
`limit`	`integer`	No	No description supplied.
`offset`	`integer`	No	Skip this many scripts; use `next_offset` from a previous page

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": "list_scripts"
}

`list_test_cases`

Purpose

List test cases for a project

Parameters

Parameter	Type	Required	Description
`project_id`	`integer`	Yes	No description supplied.
`limit`	`integer`	No	No description supplied.
`offset`	`integer`	No	No description supplied.

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": "list_test_cases"
}

`refresh_repository`

Purpose

Refresh an existing repository analysis at its latest commit. Private repositories reuse the stored GitHub App connection.

Parameters

Parameter	Type	Required	Description
`repo_id`	`integer`	Yes	No description supplied.
`branch`	`string`	No	Optional branch override

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": 1
  },
  "tool": "refresh_repository"
}

`search_test_cases`

Purpose

Search for test cases by title, description, or tags. Better than listing all test cases when looking for something specific.

Parameters

Parameter	Type	Required	Description
`project_id`	`integer`	Yes	Project ID to search in
`query`	`string`	Yes	Search query (searches in title, description, and tags)
`category`	`string`	No	Filter by category (optional)
`status`	`string`	No	Filter by status (optional)
`limit`	`integer`	No	Maximum number of results

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,
    "query": "your-query"
  },
  "tool": "search_test_cases"
}

`test_deploy_integration`

Purpose

Record a test-ping against a deploy integration to mark it active without waiting for a real deploy. Useful to confirm the integration is wired up after pasting the webhook into Vercel/Netlify.

Parameters

Parameter	Type	Required	Description
`project_id`	`integer`	Yes	The QM project ID.
`integration_id`	`integer`	Yes	The integration ID to ping.

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": {
    "integration_id": 1,
    "project_id": 1
  },
  "tool": "test_deploy_integration"
}

`update_project`

Purpose

Update an existing project (e.g., set main_url for AI crawl)

Parameters

Parameter	Type	Required	Description
`project_id`	`integer`	Yes	No description supplied.
`name`	`string`	No	No description supplied.
`description`	`string`	No	No description supplied.
`main_url`	`string`	No	No description supplied.

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": "update_project"
}

`update_project_pipeline_gates`

Purpose

Toggle PR-pipeline gate flags on a project. Gates live in project.test_frameworks and control which checks run on each pull request. Only the known gate keys are accepted; all other settings (model config, etc.) are preserved. Pass a gate as true/false. Credit-spending gates (ai_review, sast, bola) default OFF when absent; the rest default ON.

Parameters

Parameter	Type	Required	Description
`project_id`	`integer`	Yes	The QM project ID.
`gates`	`object`	Yes	Map of gate key to boolean. Recognized keys: _pipeline_run_tests, _pipeline_run_beta, _pipeline_run_ai_review, _pipeline_run_sast, _pipeline_run_sast_verify, _pipeline_run_sast_fixes, _pipeline_run_bola, _pipeline_run_tech_debt. Example: {“_pipeline_run_beta”: true}

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": {
    "gates": {},
    "project_id": 1
  },
  "tool": "update_project_pipeline_gates"
}

`update_script`

Purpose

Update an automation script’s name or code. Prefer patch over code: it sends only the lines you are changing instead of re-uploading the whole script, which is the single largest token saving available on this server.

Parameters

Parameter	Type	Required	Description
`script_id`	`integer`	Yes	Automation script ID to update
`name`	`string`	No	New script name (optional)
`code`	`string`	No	Full replacement code (optional; prefer `patch`)
`patch`	`array`	No	Anchored edits applied in order. Each old_string must appear exactly once unless replace_all is true; an ambiguous or missing anchor is rejected rather than guessed. Cannot be combined with `code`.
`expected_version`	`string`	No	Version string from a previous get_script/update_script. When supplied, the update is rejected if the script changed in the meantime.

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": {
    "script_id": 1
  },
  "tool": "update_script"
}

`update_test_case`

Purpose

Update an existing test case’s fields (title, description, steps, expected result, category, priority). Pass steps as an array of {step, expected} to replace the structured steps — that is the field automation reads, and the only way to add a mobile selector (resource_id, or the target’s visible text in quotes) to a native test case. A plain string is stored as free-text detailed instructions instead, which no generator reads as steps.

Parameters

Parameter	Type	Required	Description
`test_case_id`	`integer`	Yes	Test case ID to update
`title`	`string`	No	New title (optional)
`description`	`string`	No	New description (optional)
`steps`	`value`	No	Structured steps to replace the existing ones, or a plain string stored as detailed instructions.
`expected_result`	`string`	No	New expected result (optional)
`category`	`string`	No	New category (optional)
`priority`	`value`	No	Priority: 1-5 (integer) or critical/high/medium/low (string)

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": "update_test_case"
}