A
licenseB
qualityD
maintenanceSupercharges AI-assisted debugging of Playwright tests by parsing trace files to extract failures, action history, network logs, screenshots, and suggesting fixes.
6
0MIT
Playwright Report MCP
by nora-weisser
Playwright Report MCP
MCP-сервер, который предоставляет JSON-отчёты тестов Playwright в виде инструментов для LLM-агентов.
Требования
Python >= 3.10
uv (
brew install uvилиcurl -LsSf https://astral.sh/uv/install.sh | sh)Node.js + npx — только для
mcp dev, который запускает MCP Inspector
Related MCP server: QA Copilot MCP Server
1. Установка зависимостей
Из корня репозитория:
uv syncЭто создаёт .venv/ и устанавливает проект в режиме editable. Все приведённые ниже команды выполняются через uv run, поэтому вам никогда не придётся активировать виртуальное окружение вручную.
2. Создание Playwright JSON-отчёта
Сервер читает отчёт Playwright, созданный репортёром json. В вашем Playwright-проекте:
npx playwright test --reporter=json > results.jsonИли настройте его на постоянной основе в playwright.config.ts:
export default defineConfig({
reporter: [['json', { outputFile: 'results.json' }]],
});Файл должен содержать стандартные ключи верхнего уровня: config, suites, errors, stats.
Пример отчёта включён в состав репозитория (файл results.json), если вы просто хотите опробовать сервер.
3. Настройка пути к отчёту
Создайте файл .env в корне репозитория, указывающий на этот отчёт (рекомендуется абсолютный путь):
REPORT_PATH=/absolute/path/to/results.jsonЧтобы вместо этого использовать прилагаемый пример:
REPORT_PATH=/absolute/path/to/playwright-test-analysis-mcp/src/playwright_report_mcp/results.jsonREPORT_PATH считывается при каждом вызове инструмента, поэтому вы можете перегенерировать отчёт без перезапуска сервера. Если переменная не задана, вызовы инструментов завершаются с ошибкой REPORT_PATH environment variable is not set.
4. Запуск сервера
Интерактивная разработка (MCP Inspector)
uv run mcp dev src/playwright_report_mcp/server.pyОткрывает MCP Inspector в вашем браузере, где можно просматривать список инструментов и вызывать их вручную. Требуется npx.
Простой stdio-сервер
uv run playwright-report-mcpили, что эквивалентно:
uv run mcp run src/playwright_report_mcp/server.pyОбщается по протоколу MCP через stdin/stdout. Полезен для подключения к MCP-клиенту или для быстрого смоук-теста:
printf '{"jsonrpc":"2.0","id":1,"method":"initialize","params":{"protocolVersion":"2024-11-05","capabilities":{},"clientInfo":{"name":"t","version":"1"}}}\n' \
| uv run playwright-report-mcpВ ответ вы должны получить JSON-RPC-результат, содержащий "serverInfo":{"name":"Playwright Report",...}.
Подключение к клиенту
Зарегистрируйте сервер в Claude Desktop:
uv run mcp install src/playwright_report_mcp/server.pyИли добавьте его вручную в конфигурацию MCP-клиента (например, claude_desktop_config.json):
{
"mcpServers": {
"playwright-report": {
"command": "uv",
"args": [
"--directory",
"/absolute/path/to/playwright-test-analysis-mcp",
"run",
"playwright-report-mcp"
]
}
}
}--directory важен: он позволяет uv найти виртуальное окружение этого проекта, а load_dotenv() — файл .env.
Инструменты
Инструмент | Описание |
| Сводка последнего запуска: |
| Список упавших тестов; каждый содержит |
Запуск тестов
pytest и pytest-asyncio установлены, но в репозитории пока нет тестовых файлов, поэтому сейчас собирается 0 тестов:
uv run pytestУстранение неполадок
Симптом | Решение |
| Создайте |
|
|
| JSON — это не отчёт Playwright, созданный репортёром |
| Установите Node.js, чтобы был доступен |
Available Tools
2 toolsget_failuresA
Return failed tests of the latest Playwright test run.
| Name | Required | Description | Default |
|---|---|---|---|
No parameters | |||
Output Schema
| Name | Required | Description |
|---|---|---|
| result | Yes |
TDQS
A3.8/5.0
Behavior3/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries the full burden. It conveys read-only behavior via 'Return' and adds the useful 'latest run' scope, but it does not disclose behavior such as how empty results are handled or whether failures are ordered or grouped. These gaps are minor for a simple parameterless read and are partly covered by the output schema.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness5/5
Is the description appropriately sized, front-loaded, and free of redundancy?
A single sentence that front-loads the action and object and contains no filler. Every word contributes to selection and invocation.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness4/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the zero-parameter complexity and the presence of an output schema, the description is nearly complete for correct tool selection and invocation. The only material gap is the lack of any interaction with the sibling get_test_summary, but that is a usage-guidance concern rather than a completeness failure for this simple read.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters4/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The tool has zero parameters, so there is no parameter semantics burden for the description to carry. The baseline of 4 applies.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description states a clear action ('Return'), a precise resource ('failed tests'), and a scoping qualifier ('latest Playwright test run'). It effectively distinguishes itself from get_test_summary by focusing on failures rather than a summary.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description gives no explicit guidance about when to use this tool versus get_test_summary. It implies only that results are scoped to the latest run, but does not state when to prefer failures over a summary or whether get_test_summary is the alternative for successful tests.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
get_test_summaryA
Return summary of the latest Playwright test run.
| Name | Required | Description | Default |
|---|---|---|---|
No parameters | |||
Output Schema
| Name | Required | Description |
|---|---|---|
| flaky | Yes | |
| failed | Yes | |
| passed | Yes | |
| skipped | Yes | |
| start_time | Yes | |
| duration_ms | Yes |
TDQS
A3.5/5.0
Behavior3/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries the behavioral disclosure burden. The word 'Return' suggests a read-only operation, but the description does not mention what happens when no test run exists, whether the summary is limited by filters, or any side effects. This is minimally adequate but lacks richer behavioral context.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness5/5
Is the description appropriately sized, front-loaded, and free of redundancy?
A single, compact sentence that front-loads the action ('Return') and the object ('summary') with no filler or unnecessary detail.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness4/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a zero-parameter retrieval tool, the description is sufficiently complete: the resource is identified, the action is clear, and the presence of an output schema covers return-value details. The main gap is lack of usage guidance relative to the sibling, but that is a separate dimension.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters4/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The tool has zero parameters, so the input schema is trivially complete. The description does not need to explain parameter semantics, and the baseline of 4 applies.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose4/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the action ('Return') and the resource ('summary of the latest Playwright test run'). It distinguishes from the sibling 'get_failures' by focusing on the overall summary rather than failures, but it does not explicitly name or contrast the sibling.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
There is no guidance on when to use this tool versus 'get_failures' or any other alternative. The description implies it is for retrieving a summary, but it does not state exclusion criteria, prerequisites, or when another tool would be preferable.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
2 tool updates
v0.1.0- First observed
get_failures - First observed
get_test_summary
TDQS
A3.8/5.0
Scored across 2 tools
Disambiguation5/5
get_failures and get_test_summary have clearly distinct purposes: one retrieves only failed tests, the other an aggregate summary. There is no overlap or ambiguity between them.
Naming Consistency5/5
Both tools follow a consistent get_[noun] pattern, making the naming predictable and easy to infer. The convention is uniform across the entire set.
Tool Count3/5
With only two tools, the set is on the thin side and falls into the borderline range. The tools are focused and justified, but the count is minimal for a server that could reasonably include more report-oriented operations.
Completeness4/5
For a server scoped to the latest Playwright test run, get_failures and get_test_summary cover the primary reporting needs. Minor gaps exist—such as retrieving test details or run history—but they do not create dead ends for the core use case.
Maintenance
ActivitySlowing
ResponsivenessNo issues
Related MCP Connectors
Direct access to Cypress tests results and accessibility reports in your AI workflow.
Approved test intent, reviewed Playwright automation and run evidence, inside your editor.
Discover Playwright workflows, start runs, and inspect results in Playrunner Cloud.
Ingest and search LogsLoom logs from coding agents.
Related MCP Servers
- AlicenseAqualityBmaintenanceEnables AI assistants to summarize Playwright test runs, identify flaky tests, heuristically triage failures, generate Playwright test stubs, and retrieve recent GitHub CI status through MCP tool calls.5MIT
failure-reportofficial
AlicenseNot gradedqualityBmaintenanceEnables querying Playwright test failure reports and execution results directly from AI assistants, allowing retrieval of test outcomes, failures, and report details.MIT- AlicenseNot gradedqualityAmaintenanceEnables coding agents to validate web pages and run repeatable JSON browser scenarios, returning pass/fail results with local Playwright evidence such as screenshots, traces, and JUnit XML.7 npm1Apache 2.0