seleniumboot MCP server
2026년 11월 1일 커밋Selenium WebDriver를 통해 AI 어시스턴트가 실제 브라우저를 제어하고 Python, Java, Gherkin 기반의 자동화 테스트 코드를 생성할 수 있도록 지원합니다.
다른 이름 seleniumboot/selenium-mcp
- 스타
- 2
- Tools
- 63
- 다운로드, 30일
- —
- 최신 버전
- —
- 마지막 커밋
- 2026년 11월 1일
- 라이선스
- —
seleniumboot MCP란?
Selenium WebDriver를 통해 AI 어시스턴트가 실제 브라우저를 제어하고 Python, Java, Gherkin 기반의 자동화 테스트 코드를 생성할 수 있도록 지원합니다. 63개 도구를 제공합니다. 예: start_browser, navigate, take_screenshot.
프로젝트 README에서 생성된 요약
seleniumboot MCP server 정보
selenium-mcp는 AI 어시스턴트를 사용하는 개발자가 웹 브라우저 상호작용을 자동화하고 녹화된 세션으로부터 테스트 스크립트를 생성할 수 있게 해줍니다. Claude Desktop, GitHub Copilot 또는 JetBrains AI Assistant에 연결하여 AI가 실제 Chrome 브라우저를 제어하며 페이지 탐색, 요소 상호작용 및 어설션(assertion)을 수행할 수 있습니다. 브라우저 생명주기를 자동으로 관리하므로, 수동으로 ChromeDriver를 설정할 필요 없이 첫 사용 시 Chrome이 자동으로 실행됩니다.
사용자는 43개의 기본 도구를 통해 브라우저와 상호작용하거나, SELENIUM_MCP_TOOLS 환경 변수를 all로 설정하여 77개의 도구로 확장할 수 있습니다. 이 서버는 실제 브라우저 동작을 Python, Java, Gherkin을 포함한 다양한 프레임워크에서 즉시 실행 가능한 코드로 변환하는 데 특화되어 있습니다. TestNG, JUnit 5, Cucumber와 같은 특정 Java 출력 방식과 Page Object Model 구조를 지원합니다. 이를 통해 자연어 지시와 정식 자동화 테스트 스위트 사이의 간극을 메우고자 하는 QA 엔지니어와 개발자에게 전문적인 도구를 제공합니다.
활용 사례
- 1브라우저 탐색 자동화사이트 로그인이나 양식 작성과 같은 특정 웹 작업을 수행하도록 AI에게 지시합니다.
- 2테스트 코드 생성녹화된 브라우저 세션을 구조화된 Java TestNG 또는 Gherkin 테스트 파일로 변환합니다.
프로젝트의 README를 바탕으로 작성되었습니다. 모든 활용 사례는 해당 내용의 인용문과 대조하여 확인합니다.
seleniumboot MCP 도구 63
README에서 감지됨start_browsernavigatetake_screenshotget_page_titleget_current_urlget_page_sourceexecute_scriptrefreshswitch_to_windowopen_new_tabclose_current_tablist_windows
| start_browser | — | |
| navigate | — | |
| take_screenshot | — | |
| get_page_title | — | |
| get_current_url | — | |
| get_page_source | — | |
| execute_script | — | |
| refresh | — | |
| switch_to_window | — | |
| open_new_tab | — | |
| close_current_tab | — | |
| list_windows | — |
도구 63개 모두 보기도구 수 줄이기
close_browserscroll_to_topscroll_to_bottomscroll_byemulate_deviceget_console_logswait_for_network_idleinspect_pageget_network_logsmock_responseclear_mock_responsescompare_screenshotcheck_accessibilityfind_elementfind_elementsclicktype_textget_textget_attributeselect_optionhoverdouble_clickright_clickdrag_and_dropis_displayedis_enabledwait_for_elementscroll_to_elementclear_fieldsend_keysupload_fileget_alert_texttype_in_alertswitch_to_frameswitch_to_default_contentfind_shadow_elementget_table_datafill_formget_healed_locatorsclear_healed_locatorsassert_titleassert_urlassert_textassert_element_visibleassert_element_not_visibleassert_attributeassert_page_containsassert_element_countgenerateget_session_logclear_session_log
| close_browser | — | |
| scroll_to_top | — | |
| scroll_to_bottom | — | |
| scroll_by | — | |
| emulate_device | — | |
| get_console_logs | — | |
| wait_for_network_idle | — | |
| inspect_page | — | |
| get_network_logs | — | |
| mock_response | — | |
| clear_mock_responses | — | |
| compare_screenshot | — | |
| check_accessibility | — | |
| find_element | — | |
| find_elements | — | |
| click | — | |
| type_text | — | |
| get_text | — | |
| get_attribute | — | |
| select_option | — | |
| hover | — | |
| double_click | — | |
| right_click | — | |
| drag_and_drop | — | |
| is_displayed | — | |
| is_enabled | — | |
| wait_for_element | — | |
| scroll_to_element | — | |
| clear_field | — | |
| send_keys | — | |
| upload_file | — | |
| get_alert_text | — | |
| type_in_alert | — | |
| switch_to_frame | — | |
| switch_to_default_content | — | |
| find_shadow_element | — | |
| get_table_data | — | |
| fill_form | — | |
| get_healed_locators | — | |
| clear_healed_locators | — | |
| assert_title | — | |
| assert_url | — | |
| assert_text | — | |
| assert_element_visible | — | |
| assert_element_not_visible | — | |
| assert_attribute | — | |
| assert_page_contains | — | |
| assert_element_count | — | |
| generate | — | |
| get_session_log | — | |
| clear_session_log | — |
구성
SELENIUM_MCP_TOOLS
| 이름 | 설명 | 유형 |
|---|---|---|
| SELENIUM_MCP_TOOLS | — |
자동 검사
2026년 11월 14일에 실행됨전체 보고서 →아직 인증되지 않았습니다. 서버는 80점 이상의 점수, 심각한 결함 없음, 그리고 검사에 충분한 데이터를 갖추어야 합니다. 검사 방식 · 점수를 높이기 위해 수정할 항목
- 소스 저장소 연결 및 접근 가능seleniumboot/selenium-mcp is public and reachablegithub.com/seleniumboot/selenium-mcp ↗통과
- 패키지가 이 저장소를 소스로 명시검사되지 않음
- 빌드 출처(Sigstore 증명)검사되지 않음
- 오픈 소스 라이선스 (OSI)No license결함 발견
- 최근 1년 내 커밋 또는 릴리스Last commit or release 2026-11-01github.com/seleniumboot/selenium-mcp ↗통과
- OpenSSF Scorecard검사되지 않음
- 패키지 이름이 인기 패키지와 유사하지 않음검사되지 않음
- 패키지 및 해당 종속성에 중요한 보안 권고 없음검사되지 않음
- 모델에 대한 숨겨진 지침 없음63 tool descriptions and the README read; no override phrases, credential paths or hidden characters통과
- 파괴적인 도구에 라벨 표시됨검사되지 않음
- 원격 엔드포인트가 MCP 핸드셰이크에 응답검사되지 않음
README
GitHub에서 보기seleniumboot-mcp
A Python Model Context Protocol (MCP) server for Selenium WebDriver automation.
Let Claude or GitHub Copilot control a real browser — navigate pages, interact with elements,
run assertions, and generate ready-to-run Java TestNG / JUnit 5 / Cucumber / pytest test code from recorded sessions.
43 tools by default (77 with SELENIUM_MCP_TOOLS=all). No ChromeDriver setup. Browser auto-starts on first use.
Demo
Installation
pip install seleniumboot-mcp
Requires Python 3.10+ and Chrome. No separate ChromeDriver needed — Selenium Manager handles it automatically.
Setup
VS Code — Marketplace Extension (easiest)
Install Selenium Boot MCP from the VS Code Marketplace.
The extension automatically:
- Registers the MCP server with GitHub Copilot (no config file needed)
- Creates a
.mcp.jsonin your project so Claude Code detects it on next open - Prompts to
pip install seleniumboot-mcpif the Python package is missing
When Claude Code asks "Allow MCP server seleniumboot?" — click Allow.
JetBrains IDEs — Marketplace Plugin
Install Selenium Boot MCP from Settings → Plugins → Marketplace (search "Selenium Boot MCP"), or from the plugin page.
The plugin registers the MCP server with the JetBrains AI Assistant and prompts to
pip install seleniumboot-mcp if the Python package is missing. Use
Tools → Selenium Boot MCP to install/upgrade, register, or check status.
VS Code — Manual
Add .vscode/mcp.json to your project root (for GitHub Copilot):
{
"servers": {
"selenium": {
"type": "stdio",
"command": "seleniumboot-mcp"
}
}
}
For Claude Code, add .mcp.json to your project root:
{
"mcpServers": {
"seleniumboot": {
"command": "seleniumboot-mcp",
"args": []
}
}
}
Open the project in VS Code → Claude Code will prompt to approve the server → done.
Claude Desktop
Edit your Claude Desktop config:
- Windows:
%APPDATA%\claude-desktop\config.json - macOS:
~/.config/claude-desktop/config.json
{
"mcpServers": {
"selenium": {
"command": "seleniumboot-mcp"
}
}
}
Restart Claude Desktop.
How to use
Once the server is running, talk to Claude naturally — no start_browser call needed, Chrome launches automatically on first use:
Go to https://myapp.com and fill the login form with admin/password, then click Login
Assert the dashboard heading is visible
Generate a Java TestNG test class for everything we just did
Generate a Gherkin feature file and step definitions for the login flow
Claude controls the real browser, records every action, and on request generates complete test code ready to paste into your Maven or Gradle project.
Migrating an existing Selenium project
The migrate tool runs selenium-boot-migrator's
read-only analyze on a project and returns its JSON report (what maps cleanly, what needs a human).
It needs Java 17+. On first use it downloads the pinned migrator release (v0.1.2) from GitHub
into ~/.cache/seleniumboot-mcp/, verifies its SHA-256, and reuses it afterwards; this is the only
network call the tool makes. To skip the download, set SELENIUM_BOOT_MIGRATOR_JAR to a jar you
built, or put a selenium-boot-migrator launcher on PATH. It never edits your project.
Tools (77 total; 43 exposed by default)
Reducing token use
Tool definitions are sent to the model every session. Since 0.8.0 the server exposes the
core profile by default: 43 tools, ~3.9k tokens, covering the record-and-generate workflow
(browser, elements, assertions, the single generate tool for every output target, and migrate).
Cookies, storage, windows/tabs, network mocking, device emulation, screenshot-diff,
accessibility, healing, shadow DOM, tables and double/right-click/drag are left out.
Set SELENIUM_MCP_TOOLS=all to expose all 77 (~6.4k tokens).
{ "mcpServers": { "selenium": { "command": "seleniumboot-mcp", "env": { "SELENIUM_MCP_TOOLS": "all" } } } }
Browser
| Tool | Description |
|---|---|
start_browser |
Optional — Chrome auto-starts on first use. Use this to pick Firefox, enable headless, or set window size |
navigate |
Go to a URL |
take_screenshot |
Capture page as an inline image |
get_page_title |
Return page title |
get_current_url |
Return current URL |
get_page_source |
Return full HTML source |
execute_script |
Run JavaScript |
go_back / go_forward |
Browser history |
refresh |
Reload page |
switch_to_window |
Switch between tabs by index |
open_new_tab |
Open a new browser tab, optionally at a URL |
close_current_tab |
Close the active tab and switch to the previous |
list_windows |
List all open tabs with index, title, and URL |
close_browser |
Quit the browser |
scroll_to_top |
Scroll page to the top |
scroll_to_bottom |
Scroll page to the bottom |
scroll_by |
Scroll page by x/y pixels |
emulate_device |
Emulate a mobile device (iPhone, iPad, Pixel, Galaxy) via CDP |
get_console_logs |
Get browser console errors/warnings/info (Chrome) |
get_cookies / set_cookie |
Read or write a cookie |
delete_cookie / delete_all_cookies |
Remove cookies |
get_local_storage / set_local_storage |
Read or write localStorage |
get_session_storage / set_session_storage |
Read or write sessionStorage |
wait_for_network_idle |
Wait until XHR/fetch traffic is quiet — essential for SPAs |
inspect_page |
Discover all inputs, buttons, selects, links with best-fit CSS selectors |
get_network_logs |
Captured XHR/fetch requests — method, URL, status, timing |
mock_response |
Stub fetch/XHR by URL pattern with a canned response |
clear_mock_responses |
Remove all active mock rules |
compare_screenshot |
Pixel diff against a saved baseline — visual regression |
check_accessibility |
Built-in WCAG audit — alt text, labels, headings, keyboard access |
Elements
| Tool | Description |
|---|---|
find_element |
Find element, return tag/text/state |
find_elements |
Find all matching elements |
click |
Click with explicit wait |
type_text |
Clear + type into input |
get_text |
Get visible text |
get_attribute |
Get any attribute value |
select_option |
Select from <select> by text, value, or index |
hover |
Mouse hover |
double_click |
Double click |
right_click |
Context menu click |
drag_and_drop |
Drag source → target |
is_displayed |
Check visibility |
is_enabled |
Check enabled state |
wait_for_element |
Wait: visible / clickable / present / invisible |
scroll_to_element |
Scroll element into view |
clear_field |
Clear input field |
send_keys |
Send special keys (Tab, Enter, Escape, Ctrl+A, F5, …) |
upload_file |
Upload a file via <input type="file"> |
accept_alert / dismiss_alert |
Handle JS alert/confirm dialogs |
get_alert_text |
Read the message from an alert |
type_in_alert |
Type into a JS prompt and accept |
switch_to_frame |
Focus into an iframe by index, name, or selector |
switch_to_default_content |
Return to the main page from a frame |
find_shadow_element |
Find element inside a shadow DOM |
get_table_data |
Extract an HTML table as a formatted text grid |
fill_form |
Fill multiple fields at once — auto-detects input/select/checkbox/radio |
get_healed_locators |
View all self-healed selector mappings for the session |
clear_healed_locators |
Reset the self-healing cache |
Assertions
| Tool | Description |
|---|---|
assert_title |
Page title equals/contains |
assert_url |
URL equals/contains |
assert_text |
Element text equals/contains |
assert_element_visible |
Element is visible |
assert_element_not_visible |
Element is hidden or absent |
assert_attribute |
Element attribute has expected value |
assert_page_contains |
Page body contains a string |
assert_element_count |
Count of matching elements equals expected |
Codegen
| Tool | Description |
|---|---|
generate |
Test code or CI config from the session. language: python, java, csharp, gherkin, playwright, github_actions, jenkins, gitlab_ci. Java: framework = testng / junit5 / selenium_boot, kind = test / page_object. |
get_session_log |
View recorded actions |
clear_session_log |
Reset the session recording |
Codegen Examples
Java TestNG
Go to https://myapp.com/login, enter admin/password, click Login
→ Generate a Java TestNG test
public class LoginTest {
@BeforeMethod public void setUp() { driver = new ChromeDriver(); ... }
@AfterMethod public void tearDown() { driver.quit(); }
@Test
public void recordedFlowTest() {
driver.get("https://myapp.com/login");
WebElement f = wait.until(visibilityOf(By.cssSelector("#username")));
f.clear(); f.sendKeys("admin");
wait.until(elementToBeClickable(By.cssSelector("button[type='submit']"))).click();
}
}
Page Object Model
Generate a Java Page Object for the login page
// LoginPage.java
public class LoginPage {
private final By usernameField = By.cssSelector("#username");
private final By submitButton = By.cssSelector("button[type='submit']");
public LoginPage enterUsernameField(String text) { ... return this; }
public LoginPage clickSubmitButton() { ... return this; }
}
// LoginTest.java
public class LoginTest {
@Test public void recordedFlowTest() {
driver.get("https://myapp.com/login");
page.enterUsernameField("admin").clickSubmitButton();
}
}
Cucumber / Gherkin
Generate a Gherkin feature file and step definitions for the login flow
Feature: Login
Scenario: User logs in with valid credentials
Given I navigate to "https://myapp.com/login"
And I enter "admin" in the username field
And I enter "password" in the password field
And I click the submit button
// LoginSteps.java
public class LoginSteps {
@Given("I navigate to {string}")
public void iNavigateTo(String url) { driver.get(url); }
@And("I enter {string} in the username field")
public void iEnterInUsernameField(String text) { ... el.sendKeys(text); }
@And("I click the submit button")
public void iClickTheSubmitButton() { wait.until(...).click(); }
}
Selenium Boot projects
The Java examples above are raw Selenium: you own the ChromeDriver/WebDriverWait lifecycle
and get plain TestNG/JUnit 5 asserts. If the project you're working in has
Selenium Boot — detected automatically from selenium-boot.yml or
the io.github.seleniumboot dependency, no flag needed — the same tools emit framework-native
code instead: classes extend BaseTest/BaseJUnit5Test/BaseCucumberSteps, there's no driver
lifecycle boilerplate to write, locators follow an accessibility-first ladder
(getByRole/getByLabel/getByTestId), and assertions are web-first
(assertThat(locator).isVisible()/.hasText()) instead of raw TestNG/JUnit calls.
If no Selenium Boot project is detected, generated Java now includes a short comment noting it as an option, with a link — nothing else changes, and Python/C# output is unaffected either way.
Self-Healing Locators
When a selector fails to find an element, seleniumboot-mcp automatically tries alternative strategies before giving up:
| Primary selector | Alternatives tried |
|---|---|
#my-id (CSS) |
by=id "my-id", [id='my-id'] |
.my-class (CSS) |
by=class "my-class", [class*='my-class'] |
input[type='email'] (CSS) |
//input[@type='email'] (XPath) |
//button[@id='ok'] (XPath) |
button[id='ok'] (CSS), by=id "ok" |
"A, B" comma list |
tries A first, then B |
Successful fallbacks are cached so the healed selector is reused automatically. Use get_healed_locators to inspect the cache and update your test code, and clear_healed_locators to start fresh.
Links
- GitHub: github.com/seleniumboot/selenium-mcp
- PyPI: pypi.org/project/seleniumboot-mcp
- VS Code Marketplace: marketplace.visualstudio.com
Roadmap
- Java TestNG / JUnit 5 / Python pytest code generation
- Screenshot returned as
ImageContent(renders inline in Claude) - Full session recording — hover, double_click, right_click, scroll, select_option
- Codegen for hover, drag-and-drop, select, scroll in Java and Python templates
- Auto-start browser on first use (no explicit
start_browserneeded) - Page Object Model generation (
generatewithlanguage=java, kind=page_object) - Cucumber / Gherkin step generation (
generatewithlanguage=gherkin) - Self-healing locators — automatic fallback when a selector breaks
- Alert/dialog handling, iframe switching, shadow DOM, table extraction
- Cookie, localStorage, sessionStorage management
- Mobile device emulation via Chrome DevTools Protocol
- Special key sending (Tab, Enter, F-keys, Ctrl+A, …)
- File upload via
<input type="file"> - Browser console log capture
- Multi-tab management (open, close, list)
- Page scroll (top, bottom, by pixels)
- C# NUnit + Selenium codegen
- GitHub Actions CI workflow generator (Maven / Gradle / pytest)
- Playwright TypeScript migration hints
- CI/CD config for Jenkins / GitLab CI
License
MIT
seleniumboot MCP 질문
seleniumboot MCP는 어떤 도구를 제공하나요?
63개 도구를 제공합니다. 예: start_browser, navigate, take_screenshot, get_page_title, get_current_url.
ChromeDriver를 별도로 설치해야 하나요?
아니요, Selenium Manager가 자동으로 처리하므로 별도의 ChromeDriver 설정이 필요하지 않습니다.
이 서버는 어떤 프로그래밍 언어로 테스트 코드를 생성할 수 있나요?
Python, Java, C#, Gherkin은 물론 GitHub Actions, Jenkins, GitLab CI와 같은 CI 설정 코드도 생성할 수 있습니다.
이 서버에서 사용할 수 있는 도구는 몇 개인가요?
기본적으로 43개의 도구를 제공하며, SELENIUM_MCP_TOOLS 환경 변수를 'all'로 설정하면 77개 도구를 모두 사용할 수 있습니다.