MCP server ProvarDX CLI
✓ ПровереноПодключает ИИ-ассистентов к проектам Provar для генерации, валидации и запуска автоматизированных тестов Salesforce.
Также известен как ProvarTesting/provardx-cli, provardx-cli, @provartesting/provardx-cli
- Звёзды
- 1
- Инструменты
- —
- Загрузки, 30 дней
- —
- Последняя версия
- 1.6.5
- Последний коммит
- 24 июл. 2026 г.
- Лицензия
- BSD-3-Clause
Что такое ProvarDX CLI MCP?
ProvarDX CLI — это MCP server. Подключает ИИ-ассистентов к проектам Provar для генерации, валидации и запуска автоматизированных тестов Salesforce.
Сводка сгенерирована из README проекта
О ProvarDX CLI MCP server
Provar MCP Server напрямую подключает таких ИИ-ассистентов, как Claude Desktop, Claude Code и Cursor, к проектам Provar. Эта интеграция позволяет ИИ-агенту изучать структуру проектов, создавать Page Objects и генерировать тест-кейсы. Решение предназначено для разработчиков и тестировщиков Salesforce, которые хотят автоматизировать процессы контроля качества с помощью инструментов на базе ИИ.
Пользователи могут запускать сервер локально через npx или использовать его как глобальный плагин Salesforce CLI. Сервер предоставляет 43 различных инструмента, охватывающих инспекцию проектов, валидацию тестовых наборов и управление компонентами NitroX для LWC и Screen Flow. Поддерживаются два режима валидации: локальный режим для проверки структурных правил и режим Quality Hub API, использующий более 170 правил и систему оценки качества. Для доступа к расширенным функциям Quality Hub требуется API-ключ pv_k_, который можно получить через аккаунт Provar.
Что вы можете с ним делать
- 1Генерация автоматизации тестов SalesforceИИ-агент может создавать Page Objects и тест-кейсы непосредственно внутри структуры вашего проекта Provar.
- 2Валидация качества иерархии тестовВы можете использовать ассистента для проверки иерархии ваших тестов на соответствие обширным наборам правил для получения оценок качества.
- 3Управление сложными объектами компонентовСервер позволяет ИИ работать с объектными страницами компонентов гибридной модели NitroX для различных элементов Salesforce.
- 4Глубокая проверка по правиламРазработчики могут выполнять расширенную валидацию через Quality Hub API, проверяя соответствие более чем 170 специфическим правилам.
Взято из README проекта. Каждый вариант использования проверен на соответствие цитате из него.
Как установить ProvarDX CLI MCP
Форматы проверены 10 ноя 2026Добавить в CursorДобавить в GooseУстановка ProvarDX CLI MCP в Claude Code
$ claude mcp add provardx-cli -- npx -y @provartesting/provardx-cliУстановка ProvarDX CLI MCP в Cursor
~/.cursor/mcp.json
{
"mcpServers": {
"provardx-cli": {
"command": "npx",
"args": [
"-y",
"@provartesting/provardx-cli"
]
}
}
}Установка ProvarDX CLI MCP в VS Code
.vscode/mcp.json
{
"servers": {
"provardx-cli": {
"type": "stdio",
"command": "npx",
"args": [
"-y",
"@provartesting/provardx-cli"
]
}
}
}Установка ProvarDX CLI MCP в VS Code CLI
$ code --add-mcp '{"name":"provardx-cli","type":"stdio","command":"npx","args":["-y","@provartesting/provardx-cli"]}'Установка ProvarDX CLI MCP в Claude Desktop
claude_desktop_config.json
{
"mcpServers": {
"provardx-cli": {
"command": "npx",
"args": [
"-y",
"@provartesting/provardx-cli"
]
}
}
}Установка ProvarDX CLI MCP в Codex
$ codex mcp add provardx-cli -- npx -y @provartesting/provardx-cliУстановка ProvarDX CLI MCP в Codex config.toml
~/.codex/config.toml
[mcp_servers.provardx-cli] command = "npx" args = ["-y", "@provartesting/provardx-cli"]
Установка ProvarDX CLI MCP в Gemini CLI
$ gemini mcp add -s user provardx-cli npx -- -y @provartesting/provardx-cliУстановка ProvarDX CLI MCP в Gemini settings.json
~/.gemini/settings.json
{
"mcpServers": {
"provardx-cli": {
"command": "npx",
"args": [
"-y",
"@provartesting/provardx-cli"
]
}
}
}Автоматические проверки
Запущено 15 нояб. 2026 г.Полный отчёт →Прошло наши автоматизированные проверки. Это не аудит безопасности: изучите код и предоставьте серверу минимально необходимый доступ. Как работают проверки
- Связанный и доступный исходный репозиторийprovartesting/provardx-cli is public and reachablegithub.com/provartesting/provardx-cli ↗Пройдено
- Пакет указывает этот репозиторий как источникНе проверялось
- Происхождение сборки (аттестация Sigstore)No build attestation published for this releaseНе проверялось
- Open source лицензия (OSI)BSD-3-Clausespdx.org/licenses/BSD-3-Clause.html ↗Пройдено
- Коммит или релиз за последний годLast commit or release 2026-07-24github.com/provartesting/provardx-cli ↗Пройдено
- OpenSSF ScorecardНе проверялось
- Имя пакета не похоже на популярный пакетNo popular package one edit away from @provartesting/provardx-cliПройдено
- Нет критических предупреждений в пакете или его зависимостях351 resolved dependencies checked; no critical advisoryosv.dev ↗Пройдено
- Нет скрытых инструкций для модели0 tool descriptions and the README read; no override phrases, credential paths or hidden charactersПройдено
- Деструктивные инструменты помеченыНе проверялось
- Удалённая конечная точка отвечает на рукопожатие MCPНе проверялось
README
Открыть на GitHub@provartesting/provardx-cli
What is the ProvarDX CLI?
The Provar DX CLI is a Salesforce CLI plugin for Provar customers who want to automate the execution of tests using Provar Automation, and the reporting of test results and other quality-related metrics to Provar Quality Hub.
Installation, Update, and Uninstall
Requires Node.js 18–24 (LTS 22 recommended). Node 25+ is not yet supported due to a breaking change in a transitive dependency. Check with node --version.
Install the plugin
$ sf plugins install @provartesting/provardx-cli
Update plugins
$ sf plugins update
Uninstall the plugin
$ sf plugins uninstall @provartesting/provardx-cli
MCP Server (AI-Assisted Quality)
The Provar DX CLI includes a built-in Model Context Protocol (MCP) server that connects AI assistants (Claude Desktop, Claude Code, Cursor) directly to your Provar project. Once connected, an AI agent can inspect your project structure, generate Page Objects and test cases, validate every level of the test hierarchy with quality scores, and work with NitroX (Hybrid Model) component page objects for LWC, Screen Flow, Industry Components, Experience Cloud, and HTML5.
Validation runs in two modes: local only (structural rules, no key required) or Quality Hub API (170+ rules, quality scoring — requires a pv_k_ API key). Don't have an account? Request access.
Quick setup
Requires: Provar Automation IDE installed with an activated license. Node.js 18–24 must be on your PATH.
Option A — Zero-install (recommended for Claude Desktop)
No prior setup needed. Paste this into your Claude Desktop config file and restart the app:
- macOS:
~/Library/Application Support/Claude/claude_desktop_config.json - Windows:
%APPDATA%\Claude\claude_desktop_config.json
{
"mcpServers": {
"provar": {
"command": "npx",
"args": ["-y", "@provartesting/provardx-cli", "mcp", "start", "--allowed-paths", "/path/to/your/provar/project"]
}
}
}
npx -y downloads the package automatically on first use — no sf or separate install step required.
Claude Code — run once to register the server:
claude mcp add provar -s user -- npx -y @provartesting/provardx-cli mcp start --allowed-paths /path/to/your/provar/project
Option B — Global sf plugin install
Prefer a persistent global install? Install once, then use the sf command:
# 1. Install the plugin
sf plugins install @provartesting/provardx-cli
# 2. (Optional) Authenticate for full 170+ rule validation
sf provar auth login
Claude Desktop config using the global install:
{
"mcpServers": {
"provar": {
"command": "sf",
"args": ["provar", "mcp", "start", "--allowed-paths", "/path/to/your/provar/project"]
}
}
}
Windows (Claude Desktop): Use
sf.cmdinstead ofsfif the server fails to start.
Claude Code using the global install:
claude mcp add provar -s user -- sf provar mcp start --allowed-paths /path/to/your/provar/project
📖 docs/mcp.md — full setup, all 43 tools, 6 resources, 11 MCP prompts, troubleshooting.
Commands
sf provar auth loginsf provar auth rotatesf provar auth statussf provar auth clearsf provar mcp startsf provar config getsf provar config setsf provar automation config generatesf provar automation config loadsf provar automation config validatesf provar automation config getsf provar automation config setsf provar automation setupsf provar automation project compilesf provar automation metadata downloadsf provar automation test runsf provar quality-hub connectsf provar quality-hub displaysf provar quality-hub opensf provar quality-hub testcase retrievesf provar quality-hub test runsf provar quality-hub test run reportsf provar quality-hub test run abortsf provar manager connect(deprecated — usesf provar quality-hub connect)sf provar manager display(deprecated — usesf provar quality-hub display)sf provar manager open(deprecated — usesf provar quality-hub open)sf provar manager testcase retrieve(deprecated — usesf provar quality-hub testcase retrieve)sf provar manager test run(deprecated — usesf provar quality-hub test run)sf provar manager test run report(deprecated — usesf provar quality-hub test run report)sf provar manager test run abort(deprecated — usesf provar quality-hub test run abort)
sf provar auth login
Log in to Provar Quality Hub and store your API key.
USAGE
$ sf provar auth login [--url <value>]
FLAGS
--url=<value> Override the Quality Hub API base URL (for non-production environments).
DESCRIPTION
Opens a browser to the Provar login page. After you authenticate, your API key is
stored at ~/.provar/credentials.json and used automatically by the Provar MCP tools
and CI/CD integrations. The key is valid for approximately 90 days.
For CI/CD pipelines (GitHub Actions, Jenkins, etc.) where a browser cannot open:
run sf provar auth login once on your local machine, copy the api_key value from
~/.provar/credentials.json, and store it as the PROVAR_API_KEY environment variable
or secret in your pipeline. Rotate the secret every ~90 days when the key expires.
Don't have an account? Request access at:
https://aqqlrlhga7.execute-api.us-east-1.amazonaws.com/dev/auth/request-access
EXAMPLES
Log in interactively:
$ sf provar auth login
Log in against a staging environment:
$ sf provar auth login --url https://dev.api.example.com
sf provar auth rotate
Rotate your stored API key without re-authenticating via browser.
USAGE
$ sf provar auth rotate
DESCRIPTION
Exchanges your current pv_k_ key for a new one atomically. The old key is
invalidated immediately. The new key is written to ~/.provar/credentials.json.
Use this to rotate your key on a regular schedule (~every 90 days) without
going through the browser login flow. If your current key is already expired,
run sf provar auth login instead.
EXAMPLES
Rotate the stored API key:
$ sf provar auth rotate
sf provar auth status
Show the current API key configuration and validate it against Quality Hub.
USAGE
$ sf provar auth status
DESCRIPTION
Reports whether an API key is configured, where it came from (environment variable
or credentials file), and performs a live check against the Quality Hub API to
confirm the key is still valid.
EXAMPLES
Check auth status:
$ sf provar auth status
sf provar auth clear
Remove the stored API key.
USAGE
$ sf provar auth clear
DESCRIPTION
Deletes ~/.provar/credentials.json and revokes the key server-side. After clearing,
the MCP tools fall back to local validation mode. Has no effect if no key is stored.
EXAMPLES
Remove the stored key:
$ sf provar auth clear
sf provar mcp start
Start a local MCP server for Provar tools over stdio transport.
USAGE
$ sf provar mcp start [-a <value>...]
FLAGS
-a, --allowed-paths=<value>... Allowed base directory paths for file operations.
Defaults to the current working directory.
Repeat the flag to allow multiple paths.
DESCRIPTION
Launches a stateless MCP (Model Context Protocol) server that exposes Provar tools
to AI assistants (Claude Desktop, Claude Code, Cursor) via stdio transport. All MCP
JSON-RPC communication happens over stdout; all internal logging goes to stderr.
Note: --json is not available on this command — stdout is reserved for MCP traffic.
TOOLS EXPOSED
43 tools across: project inspection & org describe, Page Object and test-case
authoring/validation, test-suite/plan validation, properties files, Quality Hub
(test runs, defects, corpus examples), Provar Automation, ANT build, and NitroX
components. See docs/mcp.md for the full catalogue with schemas and examples.
EXAMPLES
Start MCP server (accepts stdio connections from Claude Desktop / Cursor):
$ sf provar mcp start
Start with an explicit allowed path:
$ sf provar mcp start --allowed-paths /workspace/provar
Allow multiple directories:
$ sf provar mcp start -a /workspace/project-a -a /workspace/project-b
📖 Full tool documentation and client configuration: docs/mcp.md
sf provar config get
Retrieve a value from the specified JSON file.
USAGE
$ sf provar config get -f <value> [--json]
FLAGS
-f, --file-path=<value> (required) File path of the JSON file to get the property value from.
GLOBAL FLAGS
--json Format output as json.
DESCRIPTION
Retrieve a value from the specified JSON file.
EXAMPLES
Get the testEnvironment value within the environment property from the config.json file:
$ sf provar config get environment.testEnvironment -f config.json
sf provar config set
Set one or more properties in the specified JSON file.
USAGE
$ sf provar config set [--json]
FLAGS
-f, --file-path=<value> (required) File path of the JSON file to get the property value from.
GLOBAL FLAGS
--json Format output as json.
DESCRIPTION
Set one or more properties in the specified JSON file.
EXAMPLES
Set the environment to “SIT” in the config.json properties file:
$ sf provar config set environment.testEnvironment="SIT" -f config.json
Set the testEnvironment to “SIT” and the webBrowser to “Chrome”, within the environment property.
$ sf provar config set environment.testEnvironment="SIT" environment.webBrowser="Chrome" -f config.json
Set testCases to a list of test case paths in the config.json properties file.
$ sf provar config set testCases='["tests/myTestCase.testcase","tests/testSuite1/myTestCase1.testCase"]' -f config.json
sf provar automation config generate
Generate a boilerplate ProvarDX properties file.
USAGE
$ sf provar automation config generate [--json] [-p <value>]
FLAGS
-p, --properties-file=<value> (required) Path to the properties file that will be generated.
-n, --no-prompt Don't prompt to confirm file should be overwritten.
GLOBAL FLAGS
--json Format output as json.
DESCRIPTION
Generate a boilerplate property file.
EXAMPLES
Generate a basic properties file named provardx-properties.json:
$ sf provar automation config generate -p provardx-properties.json
sf provar automation config load
Validate and load a ProvarDX properties file for later use.
USAGE
$ sf provar automation config load -p <value> [--json]
FLAGS
-p, --properties-file=<value> (required) Path of the properties file to be loaded.
GLOBAL FLAGS
--json Format output as json.
DESCRIPTION
Validate and load a ProvarDX properties file for later use.
EXAMPLES
Validate that the myproperties.json file is valid.
$ sf provar automation config load -p myproperties.json
sf provar automation config validate
Check if the loaded properties file has all the required properties set.
USAGE
$ sf provar automation config validate [--json]
GLOBAL FLAGS
--json Format output as json.
DESCRIPTION
Check if the loaded properties file has all the required properties set.
EXAMPLES
Check if the loaded properties file has all the required properties set:
$ sf provar automation config validate
sf provar automation config get
Retrieve a value from the loaded properties file.
USAGE
$ sf provar automation config get [--json]
GLOBAL FLAGS
--json Format output as json.
DESCRIPTION
Retrieve a value from the loaded properties file.
EXAMPLES
Get the testEnvironment property value from the provardx-properties.json properties file:
$ sf provar automation config get environment.testEnvironment
sf provar automation config set
Set one or more properties in the loaded properties file.
USAGE
$ sf provar automation config set [--json]
GLOBAL FLAGS
--json Format output as json.
DESCRIPTION
Set one or more properties in the loaded properties file.
EXAMPLES
Set the environment to "SIT” in the provardx-properties.json properties file:
$ sf provar automation config set environment.testEnvironment="SIT"
Set the testEnvironment to "SIT” and the webBrowser to "Chrome”, within the environment property:
$ sf provar automation config set environment.testEnvironment="SIT" environment.webBrowser="Chrome"
Set testCases to a list of test case paths in the provardx-properties.json properties file:
$ sf provar automation config set testCases='["tests/myTestCase.testcase","tests/testSuite1/myTestCase1.testCase"]'
sf provar automation setup
Download and install Provar Automation.
USAGE
$ sf provar automation setup [--json] [-v <value>]
FLAGS
-v, --version=<value> Provar Automation build version number.
GLOBAL FLAGS
--json Format output as json.
DESCRIPTION
Download and install Provar Automation.
EXAMPLES
Install version Provar Automation version 2.12.1:
$ sf provar automation setup --version 2.12.1
sf provar automation project compile
Compile PageObject and PageControl Java source files into object code.
USAGE
$ sf provar automation project compile [--json]
GLOBAL FLAGS
--json Format output as json.
DESCRIPTION
Compile PageObject and PageControl Java source files into object code.
EXAMPLES
Compile the project using the configuration set in the properties file:
$ sf provar automation project compile
sf provar automation metadata download
Download any required metadata for a specified Provar Salesforce connection.
USAGE
$ sf provar automation metadata download -c <value> [--json]
FLAGS
-c, --connections=<value> (required) Comma-separated list of names of Provar Salesforce connections to use, as defined in the project.
GLOBAL FLAGS
--json Format output as json.
DESCRIPTION
Download any required metadata for a specified Provar Salesforce connection.
EXAMPLES
Refresh metadata for the MySalesforceConnection connection and store it in folder set in the properties file:
$ sf provar automation metadata download -c MySalesforceConnection
sf provar automation test run
Run the tests as specified in the loaded properties file.
USAGE
$ sf provar automation test run [--json]
GLOBAL FLAGS
--json Format output as json.
DESCRIPTION
Run the tests as specified in the loaded properties file.
EXAMPLES
Run the tests as specified in the loaded properties file:
$ sf provar automation test run
sf provar quality-hub connect
Connect to a Provar Quality Hub org.
USAGE
$ sf provar quality-hub connect -o <value> [--json]
FLAGS
-o, --target-org=<value> (required) Username or alias set in the SF CLI which corresponds to the Provar Quality Hub org.
GLOBAL FLAGS
--json Format output as json.
DESCRIPTION
Load the alias or username to be used in subsequent Quality Hub commands.
EXAMPLES
Connect to the Quality Hub org stored with alias "ProvarQualityHub":
$ sf provar quality-hub connect -o ProvarQualityHub
sf provar quality-hub display
Display information about the connected Provar Quality Hub org.
USAGE
$ sf provar quality-hub display [--json]
GLOBAL FLAGS
--json Format output as json.
EXAMPLES
Display information about the connected Quality Hub org:
$ sf provar quality-hub display
sf provar quality-hub open
Open Provar Quality Hub in a browser.
USAGE
$ sf provar quality-hub open [--json]
GLOBAL FLAGS
--json Format output as json.
EXAMPLES
Open Quality Hub in a browser:
$ sf provar quality-hub open
sf provar quality-hub testcase retrieve
Retrieve test cases related to the provided user stories or metadata components.
USAGE
$ sf provar quality-hub testcase retrieve -p <value> -t Apex|ProvarAutomation [--json] [-m <value>] [-f <value>] [-i <value>] [-o <value>] [-n <value>] [-l <value>]
FLAGS
-f, --metadata-file=<value> Path to a text file containing the list of metadata components.
-i, --issues=<value> Comma-separated list of issue IDs or keys.
-l, --test-plan=<value> Test Plan name. Use to retrieve test instance file paths.
-m, --metadata-components=<value> Semicolon-separated list of metadata components.
-n, --ignore-metadata=<value> Semicolon-separated list of metadata types to ignore.
-o, --output=<value> Output to a specific file instead of stdout.
-p, --test-project=<value> (required) Test Project key to filter by.
-t, --test-automation-tool=<option> (required) <options: Apex|ProvarAutomation>
EXAMPLES
Retrieve Provar Automation test cases for user story "TM-766":
$ sf provar quality-hub testcase retrieve -p PAT -t ProvarAutomation -i "TM-766" --json
sf provar quality-hub test run
Run tests via Provar Quality Hub.
USAGE
$ sf provar quality-hub test run -f <value> [--json] [-y] [-w <value>] [-p <value>] [-o <value>] [-r <value>]
FLAGS
-f, --configuration-file=<value> (required) Path to the configuration file.
-o, --output=<value> Output to a specific file instead of stdout.
-p, --polling-interval=<value> [default: 60] Polling interval in seconds.
-r, --result-format=<value> [default: human] Format of the test results.
-w, --wait=<value> Polling timeout in minutes.
-y, --synchronous Run synchronously.
EXAMPLES
Run tests and store results as JSON:
$ sf provar quality-hub test run -f config/run-grid-tests.json -w 10 -p 30 -r json -o results.json
sf provar quality-hub test run report
Check or poll for the status of a Quality Hub test run.
USAGE
$ sf provar quality-hub test run report -i <value> [--json] [-r <value>] [-o <value>]
FLAGS
-i, --test-run=<value> (required) Test run ID.
-o, --output=<value> Output to a specific file instead of stdout.
-r, --result-format=<value> [default: human] Format of the test results.
EXAMPLES
Retrieve results for a test run:
$ sf provar quality-hub test run report -i 45f70417-df21-4917-a667-abc2ee46dc63 -r json -o results.json
sf provar quality-hub test run abort
Abort an in-progress test run triggered via Provar Quality Hub.
USAGE
$ sf provar quality-hub test run abort -i <value> [--json] [-p <value>] [-w <value>]
FLAGS
-i, --test-run=<value> (required) Test run ID.
-p, --polling-interval=<value> [default: 30] Polling interval in seconds.
-w, --wait=<value> [default: 2] Polling timeout in minutes.
EXAMPLES
Abort a test run:
$ sf provar quality-hub test run abort -i 45f70417-df21-4917-a667-abc2ee46dc63
Deprecated commands: The
sf provar manager *commands below are retained for backwards compatibility and will print a deprecation warning when used. Use the equivalentsf provar quality-hub *commands above for all new pipelines.
sf provar manager connect
Load the alias or username to be used in subsequent commands to connect to Provar Manager.
USAGE
$ sf provar manager connect -o <value> [--json]
FLAGS
-o, --target-org=<value> (required) Username or alias set in the SF CLI which corresponds to the Provar Manager org.
GLOBAL FLAGS
--json Format output as json.
DESCRIPTION
Load the alias or username to be used in subsequent commands to connect to Provar Manager.
EXAMPLES
Connect to the Provar Manager org that has been previously authorised using the SF CLI, and stored with the alias "ProvarManager":
$ sf provar manager connect -o ProvarManager
sf provar manager display
Display information about the connected Provar Manager org.
USAGE
$ sf provar manager display [--json]
GLOBAL FLAGS
--json Format output as json.
DESCRIPTION
Display information about the connected Provar Manager org.
EXAMPLES
Display information about the connected Provar Manager org:
$ sf provar manager display
sf provar manager open
Open Provar Manager in a browser.
USAGE
$ sf provar manager open [--json]
GLOBAL FLAGS
--json Format output as json.
DESCRIPTION
Open Provar Manager in a browser.
EXAMPLES
Open Provar Manager in a browser:
$ sf provar manager open
Вопросы о ProvarDX CLI MCP
Как добавить ProvarDX CLI MCP в Claude Code?
Выполните claude mcp add provardx-cli -- npx -y @provartesting/provardx-cli в терминале. Добавьте --scope user, чтобы сервер был доступен во всех проектах.
Как добавить ProvarDX CLI MCP в Cursor?
Откройте ~/.cursor/mcp.json и добавьте сервер в mcpServers, используя конфигурацию Cursor из раздела установки выше.
Что может делать ИИ-агент с помощью Provar MCP server?
ИИ-агент может анализировать структуру проектов, создавать Page Objects и тест-кейсы, проверять иерархию тестов с помощью оценки качества и работать с компонентами NitroX.
Какие требования предъявляются к настройке MCP server?
Необходимо наличие установленной Provar Automation IDE с активной лицензией и Node.js версии 18–24, добавленной в PATH.
Как включить расширенную валидацию по более чем 170 правилам?
Для использования валидации через Quality Hub API и получения оценок качества необходимо предоставить API-ключ 'pv_k_'.