Check if your TestDino connection is working. Verifies your PAT, shows your account information, and lists available organizations and projects. Use this first to make sure everything is set up correctly and to get organization/project IDs for other tools.

Browse and filter your test runs to find specific test executions. Filter by git branch (e.g., 'develop', 'main'), time interval ('Latest', '1h', '2h', '5h', '1d', '3d', '5d', 'weekly', 'monthly', or custom date ranges), commit author, or environment (e.g., 'production', 'staging', 'development'). Supports efficient pagination using page/limit or offset/limit, or use get_all=true to fetch all results (up to 1000). Returns test run summaries with statistics (total, passed, failed, skipped, flaky counts), duration, status, branch, author, and PR information when available. Perfect for answering questions like 'What tests ran on the develop branch?' or 'Show me all test runs from last hour.' The PAT should be configured in mcp.json as TESTDINO_PAT environment variable.

Get detailed information about test runs. Shows test statistics (passed, failed, skipped, flaky), all test suites and cases, git metadata, and error details. Supports batch operations (comma-separated IDs, max 20). Use this to analyze test execution health or debug specific failures.

List test cases with comprehensive filtering options. You can filter by test run (ID or counter), status, spec file, error category, browser, tags, runtime, artifacts, error messages, attempt number, branch, time interval, environment, author, or commit hash. When using test run filters (by_branch, by_commit, by_author, by_environment, by_time_interval, by_pages, page, limit, get_all), the tool first lists test runs matching those criteria, then returns test cases from those filtered test runs. Use this to find specific test cases across your test runs.

Get detailed information about a specific test case. You can identify the test case in two ways: 1) By testcase_id (can be used alone), or 2) By testcase_name combined with testrun_id or counter (required because test cases can have the same name across different test runs). Returns error message, code snippet, file location, test steps per attempt, console logs, and optional artifacts (screenshots, videos, traces). Use steps_filter='failed_only' to return only steps that errored, stripping passing setup/hook steps. Use this to debug why a test failed or understand how it executed. Example: 'Get test case details for "Verify user can logout and login" in testrun #43'.

Fetch historical execution and failure data for a specific test case. Returns raw historical data with test run details (ID, counter, branch), test runs summary, and a debugging prompt from the API. Each execution includes its associated test run information (testRunId, testRunCounter, branch) to help correlate failures across different test runs and branches. The AI client will analyze the data to identify failure patterns, find root causes, and provide fix suggestions. Use this when you need to debug a failing test case. Example: 'Debug test case "Verify user login"'.

TestDino-backed Playwright test quality audit. This tool is a NAMED CAPABILITY, not a style of output — when the user invokes it, you MUST call this tool, not simulate it in chat. === TRIGGER PHRASES (explicit TestDino naming) === Any of the following REQUIRES an immediate tool call: 'TestDino test audit', 'Testdino Test Audit', 'Testdino audit', 'TestDino MCP audit', 'run a TestDino test audit', 'audit this with TestDino', 'I need a TestDino audit', 'TestDino audit on ', 'testdino test audit on this'. Case-insensitive. Typos like 'testdino', 'test dino', 'TD audit' with context also qualify. === MANDATORY BEHAVIOR WHEN TRIGGERED === The moment you detect a TestDino trigger phrase AND the target is Playwright test code, your FIRST and IMMEDIATE action MUST be to call this tool with action='analyze'. Before that tool call returns: - DO NOT write any audit content in chat. - DO NOT produce a header like 'TestDino Test Audit — '. - DO NOT list findings, score, severity, or recommendations. - DO NOT describe the file in audit-report language. - DO NOT simulate the TestDino audit output from your own knowledge. - Doing any of the above without calling the tool is a PROTOCOL VIOLATION — you are claiming to run a TestDino audit without actually running it. TestDino audits require the server-curated audit prompt and branch signals returned by action='analyze'; you do not have those without the tool call. The only valid first step is: test_audit(action='analyze', projectId=). Branch is OPTIONAL — pass it only if the user named one or git auto-detects it; otherwise omit it and proceed with the audit anyway (do not ask the user for a branch). Resolve projectId via health() if you don't already have it. Only AFTER that call returns do you read the local Playwright code (guided by the returned prompt + branch signals), build the audit markdown locally, and submit it via a second tool call. === PLAYWRIGHT GATE === The target code MUST be Playwright. Detect via @playwright/test imports, Playwright APIs (page./browser./context./locator(/test(/test.describe(/test.beforeEach(/test.step(/expect(page)/browserName/storageState/test.extend(), playwright.config.*, or .spec.ts/.spec.js/.test.ts/.test.js files using those APIs. If the user names TestDino but the target is NOT Playwright, politely explain TestDino's test audit only covers Playwright automated test code and offer a regular (non-TestDino) audit instead — DO NOT call the tool in that case. === WHEN NOT TO CALL THIS TOOL === If the user asks for a generic 'audit', 'test audit', 'code audit', 'security audit', 'accessibility audit', 'review', etc. WITHOUT explicitly naming TestDino, DO NOT call this tool — even if the target is Playwright test code. Those are normal AI-agent audits: read the target, write findings directly in chat. Do NOT mention TestDino, do NOT offer TestDino, do NOT say 'I can run a TestDino audit instead'. Behave as a plain AI assistant with no TestDino MCP installed. === FULL FLOW (Playwright + TestDino explicitly named) === Step 1 (IMMEDIATE): test_audit(action='analyze', projectId=..., branch=...) — no score, no findings, no markdownReport on this call. This is the mandatory first action. Step 2: Using the prompt and branch signals returned from Step 1, analyze the local Playwright test code and write the full markdown audit report to a local file (e.g. TEST-AUDIT.md). Step 3: test_audit(action='analyze', markdownReportPath=<path from Step 2>, score=..., findings=[...], recommendations=[...], reportName=...) — submits to TestDino. Scope: use 'feature' or 'spec_file' when the user names a slice like auth/login. If analyze fails with project/auth access errors, resolve projectId with health() before retrying — never fabricate a fallback pseudo-audit. Other actions: action='list' browses past submitted reports (optionally filtered by branch); action='get' retrieves a specific submitted report.

Search and list manual test cases with filtering capabilities. Use this to find specific manual test cases for QA testing, auditing, or test case management. Supports filtering by project, time, suite, status, priority, severity, type, layer, behavior, automation status, and tags.

Retrieve detailed information of a single manual test case, including steps, custom fields, preconditions, and all metadata. Activity is included inline: comments (latest), versions (latest 20 of the version history), results (latest 100 execution results across every manual run that ran this case), and linkedIssues (Jira tickets linked to the case). versions and results are READ-ONLY — they reflect what happened, you cannot mutate them. Use update_manual_test_case to add comments (updates.comments) or link issues (updates.issues).

Create a new manual test case. Use this to document new test scenarios, features, or requirements. Supports adding test steps, preconditions, postconditions, and metadata like priority, severity, and type.

Update an existing manual test case. Use this to modify test case details, steps, status, priority, or any other fields. Provide only the fields you want to update in the updates object. To add comments, pass updates.comments as an array of strings — each becomes a new comment (PAT owner is author). To link Jira issues, pass updates.issues as an array of ticket keys (e.g. ['PROJ-123']); the server looks each up in the project's connected Jira and saves with title+url, or as a plain text stub when Jira isn't connected or the ticket isn't found (same fallback as the UI).

List the test suite hierarchy to help users find suiteIds for test case creation. Use this to navigate the test suite structure and understand test organization.

Create a new test suite folder to organize test cases. Use this to create a logical grouping for related test cases. Suites can be nested by providing a parentSuiteId.

Browse releases (a.k.a. milestones) for a project. Use search to match by name; type filters by free-text release type; isCompleted filters by completion state; parentReleaseId returns the direct children of a release (releases nest up to 3 levels deep). Default page size 25 (max 200).

Get the full details of one release: dates, status, linked issues, parent/root, and rolled-up progress stats (run counts, test status breakdown). releaseId accepts either the internal _id or a counter-style ID like 'MS-12'.

Create a new release. Requires write permission (org_owner, org_admin, or org_member). Use parentReleaseId to nest under another release (max 3 levels deep). startDate/endDate are ISO date strings. isStarted/isCompleted are independent flags — startedAt/completedAt record when those transitions happened.

Modify an existing release. Send only the fields you want to change inside the updates object. Requires write permission. Fields: name, description, note, type, startDate, endDate, isStarted, isCompleted, startedAt, completedAt, linkedIssues.

Browse manual test runs for a project. Filter by status (active|closed), state (new|in_progress|on_hold|done), environment, release (releaseId), tags (csv or single), or free-text search on name. Pass releaseId='none' to list runs not attached to any release. Default page size 25 (max 200).

Get the full details of one manual test run: name, status, environment, linked release, test stats (total/passed/failed/blocked/untested), contributors, attachments, linked issues. runId accepts either the internal _id or a counter-style ID like 'RUN-12'.

Create a new manual test run. Requires write permission. selectionMode controls which test cases are included: 'all' (default — every case in the project) or 'selected' (use testCaseIds and/or suiteIds to scope). releaseId attaches the run to a release. note accepts rich HTML. IMPORTANT: tags must be a JSON array of strings here — e.g. ["smoke","regression"] — NOT the comma-separated form that list_manual_runs accepts as a filter.

Modify an existing manual test run. Send only the fields you want to change inside the updates object. Requires write permission. Allowed fields: name, note, environment, releaseId, state, forecast, tags, linkedIssues, attachments, links, selectionMode. Closed runs are read-only except for releaseId (so a run can be re-attached to a different release). IMPORTANT: updates.tags must be a JSON array of strings — e.g. ["smoke","regression"] — NOT a comma-separated string.

Get the per-case execution records inside a manual run — what the UI shows as rows in the run's test-case table. Each row carries the test case identity (caseKey like 'TC-156', title), the current assignee, and the current result/status ('untested', 'passed', 'failed', etc.). Filter by assignee (email or User _id) or result/status. Use this before update_run_test_case so you have the rtcRef for each case you want to update.

Set the assignee and/or result for one test case inside a manual run — exactly what clicking 'Assign to' and changing the result pill does in the UI. Requires write permission. rtcRef accepts the caseKey ('TC-156'), the internal tcm_rtc_... RTC ID, or the underlying test case _id. Works for both already-touched cases and 'untested' virtual cases (the server auto-creates the per-case record on first edit). IMPORTANT: updates.assigneeUserId accepts an email OR a User _id — both work. updates.result canonical values are 'untested', 'passed', 'failed', 'blocked', 'skipped', 'retest' — pass display ('Passed', 'Blocked') or canonical form, server normalizes lowercase+underscored. To assign or update multiple cases at once, call this tool in parallel (one call per case).

Browse exploratory sessions for a project. Filter by status (active|closed), state, sessionType, assigneeUserId, release (releaseId), tags, or free-text search on name. Pass releaseId='none' for sessions not attached to a release. Default page size 25 (max 200).

Get the full details of one exploratory session: name, mission, status, assignee, linked release, attachments, linked issues, findings. sessionId accepts either the internal _id or a counter-style ID like 'SES-12'.

Create a new exploratory testing session. Requires write permission. mission accepts rich HTML (the high-level charter). assigneeUserId accepts either a User _id ("user_abc...") or an email address — the email is resolved against TestDino users automatically. estimate is in minutes. Findings cannot be created here — add them in the UI. IMPORTANT: tags must be a JSON array of strings — e.g. ["exploratory","auth"] — NOT the comma-separated form that list_sessions accepts as a filter.

Modify an existing exploratory session. Send only the fields you want to change inside the updates object. Requires write permission. Allowed fields: name, mission, sessionType, config, environment, releaseId, assigneeUserId, state, estimate, tags, linkedIssues, attachments. Findings are not editable here. updates.assigneeUserId accepts either a User _id or an email address. IMPORTANT: updates.tags must be a JSON array of strings — e.g. ["exploratory","auth"] — NOT a comma-separated string.