ascended-browser MCP server
2026년 11월 9일 커밋AI agent가 대화형 자동화, 프론트엔드 QA 및 검증된 웹 작업을 수행할 수 있도록 보안이 강화된 브라우저를 제공합니다.
다른 이름 AceAtDev/ascended-browser
- 스타
- 3
- Tools
- 11
- 다운로드, 30일
- —
- 최신 버전
- —
- 마지막 커밋
- 2026년 11월 9일
- 라이선스
- MIT
ascended-browser MCP란?
AI agent가 대화형 자동화, 프론트엔드 QA 및 검증된 웹 작업을 수행할 수 있도록 보안이 강화된 브라우저를 제공합니다. 11개 도구를 제공합니다. 예: browser_open, browser_observe, browser_act.
프로젝트 README에서 생성된 요약
ascended-browser MCP server 정보
ascended-browser는 AI agent가 대화형 웹 자동화 및 프론트엔드 품질 보증을 수행할 수 있도록 지원합니다. 이 로컬 오픈 소스 MCP server는 웹사이트에서 실제 사용자처럼 보이도록 설계된 Firefox 버전인 Camoufox를 사용하여 보안이 강화된 브라우저 환경을 제공합니다. Claude Code, Codex CLI 또는 Cursor와 같은 클라이언트를 사용하는 개발자가 탐색적 테스트를 수행하고 웹 작업을 검증할 수 있도록 구축되었습니다.
사용자는 전체 양식 채우기, 커스텀 React 드롭다운에서 항목 선택, 좌표 대신 특정 이름을 통한 탐색과 같은 검증된 작업을 통해 복잡한 작업을 관리할 수 있습니다. 이 서버에는 콘솔 로그, 네트워크 요청 및 반응형 레이아웃을 검사할 수 있는 기능을 포함하여 디버깅을 위한 특화된 도구가 포함되어 있습니다. 또한 비밀번호 및 TOTP 비밀 정보와 같은 민감한 자격 증명이 AI agent에 노출되지 않도록 보장하는 저장된 로그인 시스템을 통해 안전한 세션 관리를 지원합니다.
설정은 npm 또는 Python을 통해 이루어지며, 서버는 가상 디스플레이 지원을 위해 xvfb를 사용하는 Linux 개발 환경에서 실행할 수 있습니다. 작업 후 변경 사항을 보고하여 상세한 피드백을 제공하며, Turnstile 또는 reCAPTCHA와 같은 봇 탐지 문제도 처리할 수 있습니다.
활용 사례
- 1프론트엔드 오류 디버깅에이전트가 실패한 네트워크 요청과 콘솔 오류를 식별하여 애플리케이션 버그를 진단할 수 있습니다.
- 2반응형 디자인 검증개발자가 에이전트에게 다양한 기기 브레이크포인트에서 웹사이트가 어떻게 보이는지 확인하도록 지시할 수 있습니다.
- 3복잡한 양식 입력 자동화에이전트가 검증된 작업을 사용하여 단일 작업으로 여러 필드의 양식을 완성할 수 있습니다.
- 4인증 흐름의 안전한 테스트에이전트가 실제 비밀번호를 보지 않고도 저장된 자격 증명을 사용하여 보호된 페이지에 로그인할 수 있습니다.
프로젝트의 README를 바탕으로 작성되었습니다. 모든 활용 사례는 해당 내용의 인용문과 대조하여 확인합니다.
ascended-browser MCP 도구 11
README에서 감지됨browser_openbrowser_observebrowser_actbrowser_extractbrowser_screenshotbrowser_viewportbrowser_evaluatebrowser_tabsbrowser_flowbrowser_loginwait_for_bot_wall
| browser_open | — | |
| browser_observe | — | |
| browser_act | — | |
| browser_extract | — | |
| browser_screenshot | — | |
| browser_viewport | — | |
| browser_evaluate | — | |
| browser_tabs | — | |
| browser_flow | — | |
| browser_login | — | |
| wait_for_bot_wall | — |
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 가능aceatdev/ascended-browser is public and reachablegithub.com/aceatdev/ascended-browser ↗통과
- 패키지가 이 저장소를 소스로 명시검사되지 않음
- 빌드 출처(Sigstore 증명)검사되지 않음
- 오픈 소스 라이선스 (OSI)MITspdx.org/licenses/MIT.html ↗통과
- 최근 1년 내 커밋 또는 릴리스Last commit or release 2026-11-09github.com/aceatdev/ascended-browser ↗통과
- OpenSSF Scorecard검사되지 않음
- 패키지 이름이 인기 패키지와 유사하지 않음검사되지 않음
- 패키지 및 해당 종속성에 중요한 보안 권고 없음검사되지 않음
- 모델에 대한 숨겨진 지침 없음11 tool descriptions and the README read; no override phrases, credential paths or hidden characters통과
- 파괴적인 도구에 라벨 표시됨No tool named like delete, drop or exec통과
- 원격 엔드포인트가 MCP 핸드셰이크에 응답검사되지 않음
README
GitHub에서 보기A local, open-source browser MCP server for Codex CLI, Claude Code and other MCP clients. Use it for interactive browser automation and front-end QA: inspect console logs and network requests, check responsive layouts, and collect screenshots alongside what happened on the page.
Your agent opens pages, reads them, and acts on them through verified actions: it fills a whole form in one call, picks "Mrs." from a custom React dropdown by name, and is told what the page did in response, instead of clicking coordinates and hoping.
Ascended is my own private agent workspace; this package extracts its browser so it can run on its own: Camoufox (a hardened Firefox that looks like a person's browser to the sites it visits) behind the same tool dispatcher, page reading and result formatting Ascended's own agent uses.
Start with a QA check
Read the documentation site: QA setup and interrupted-action reproduction.
Running Codex CLI over SSH and missing a browser? Connect a browser MCP on your Linux dev box with setup commands, localhost guidance and alternatives.
Practical recipes with real local-fixture screenshots:
- Find console errors and failed requests.
- Check responsive layouts.
- Test login-protected pages and session reuse.
Set up a browser MCP for Codex CLI or Claude Code and check your app. The guide covers installation, a copy-paste QA prompt, console and network inspection, bug-report structure, and what to do after an interrupted action.
- Check a local app: walk through a flow and report errors before changing code.
- Inspect the evidence: read failed requests and console errors, then capture the broken state.
- Use a Linux dev box: run the client, MCP server and app on the same machine; the guide explains how localhost behaves when you connect over SSH.
This is agent-assisted exploratory QA, not a replacement for deterministic regression tests or a validated CI integration. Browser MCP tools are also available from projects such as Playwright MCP and Chrome DevTools MCP; console and network inspection are not exclusive to this server.
See it work
Three real runs of Claude Code with only this server attached, on live sites.
The panel on the side is Claude Code's own transcript: every tool call it made
and what came back, errors included, with the real elapsed time. Waiting is
cut and tool time plays faster; the pointer, device frames, devtools panels
and outlines are drawn afterwards from the server's event log
(demo/record_demo.py), so they sit on what the agent really touched and read.
The full unedited screen recordings are in videos/unedited/
(the browser is driven through Playwright, so no OS pointer appears in them).
Front-end QA. react.dev on a phone and a tablet, dark/light, before/after screenshots, an audit outlining the real offending elements, console and network.
Browsing. Types into Wikipedia's search, finds a fact in the article, then searches YouTube and plays the first video.
Real forms. booking.com: popup, destination autocomplete, date picker, search, sort by price.
Saved logins. You save a login once; the agent signs in with it and never sees it. Built from a real run (demo/login_demo.py, then demo/login_explainer.py): the CLI's output, the screen, and the exact text and pictures the agent got back.
Click any clip for the full-quality MP4.
Install
From Python (3.11 or newer) or from npm; both run the same server.
uvx ascended-browser doctor # checks the machine; downloads nothing
uvx ascended-browser fetch # downloads the browser now (~700 MB; otherwise on first use)
npx -y ascended-browser doctor # the same, from npm
The browser is Camoufox 135.0.1-beta.24, the build every test here ran on; it is
pinned, so a newer Camoufox release never changes what your agent drives, and
any other Camoufox you have installed is left as it is. Run fetch once before
adding the server to an agent, so its first tool call does not wait for the
download.
The npm package is a small launcher: it runs the Python package with uvx
when uv is installed (uv brings its own Python),
else pipx, else a private venv made with your Python 3.11+. Use whichever
command you prefer in the configs below (npx -y ascended-browser in place of
uvx ascended-browser).
Linux: install xvfb to keep the browser on a virtual display (closest to a
real screen); without it the browser runs headless. On a display,
browser_viewport resizes the real window, so phone and tablet checks reflow
the page at true breakpoints.
Add it to your agent
Claude Code
claude mcp add ascended-browser -- uvx ascended-browser
# or: claude mcp add ascended-browser -- npx -y ascended-browser
Codex
codex mcp add ascended-browser -- uvx ascended-browser
Whether Codex asks before each browser action follows the permission mode you
pick in Codex: under Full access it just runs them; under Ask for approval
it asks first. In a sandboxed mode, codex exec cannot ask and fails every
call: use Full access, or pre-approve this server's tools by adding
default_tools_approval_mode = "approve" under [mcp_servers.ascended-browser]
in ~/.codex/config.toml.
opencode (opencode.json)
{
"mcp": {
"ascended-browser": { "type": "local", "command": ["uvx", "ascended-browser"], "enabled": true }
}
}
Cursor, Windsurf, Claude Desktop and other clients: a stdio server with
command uvx and args ["ascended-browser"], or command npx and args
["-y", "ascended-browser"].
Tools
| Tool | What it does |
|---|---|
browser_open |
Open a URL (or several at once) and return what is on the page, each control with a ref |
browser_observe |
Look at the page again, or narrow to a region, a query or a filter |
browser_act |
navigate, click, fill, fill_form, select, check, date, press, upload, scroll, wait, sequence: each verified, each answered with what changed |
browser_extract |
Read the page's text and field state, find a phrase, list every match of a CSS selector with its text and attributes (every product link, every price), or read=console, read=network, read=inspect, read=audit, read=design to debug a page |
browser_screenshot |
A picture, when an observation cannot describe it: canvas, charts, visual layout; compare_with diffs against an earlier picture or another tab |
browser_viewport |
Resize to phone/tablet/desktop (Linux), emulate dark mode, reduced motion, forced colors or offline |
browser_evaluate |
Read-only JavaScript, policy-checked |
browser_tabs |
List, close or sleep tabs |
browser_flow |
Record a task once, replay it on the next page with new values |
browser_login |
Sign in with a login you saved (see Saved logins); the agent never sees its values |
wait_for_bot_wall |
Wait out a "checking your browser" page; press a Turnstile/reCAPTCHA checkbox if one blocks a form |
Long results come back clipped, with an evidence_ref that
browser_extract pages through, so a huge page cannot flood the agent's
context.
Every action waits for the page to settle, under a hard timeout, and says
when its effect could not be confirmed. If a turn ends while one is still
running, the next turn is told instead of finding a page it cannot explain:
an interrupted click (you stopped the turn) is named in the next result for
that tab, and an action whose server died (claude -p ending, an SSH session
dropping) is listed with the first result of the next session, so the agent
checks before it repeats an order or a form.
Saved logins
Save a login once and the agent can sign in with it, without ever seeing it.
uvx ascended-browser login add github.com --username you@example.com # prompts for the password
uvx ascended-browser login add accounts.example.com --name Work --totp # also a TOTP secret (or otpauth:// URI)
uvx ascended-browser login list # names, usernames, sites; never passwords
uvx ascended-browser login edit Work --password # change only what you pass
uvx ascended-browser login remove Work
The site is the host of the sign-in page (accounts.example.com, not
example.com, when they differ); pass several for one account on several
hosts. Passwords and TOTP secrets come from a hidden prompt, or from stdin
with --password-stdin, never from the command line, where they would end up
in shell history and the process list.
Then ask your agent to sign in. browser_open tells it a saved login exists
for the page, and browser_login finds the username, password and
one-time-code fields and types the values in (submit: true also presses
the button). What the agent gets:
- Every tool result is scrubbed of every saved username, password and TOTP
secret, also URL-encoded, JSON- or HTML-escaped:
browser_observe,browser_evaluate(readinginput.valuereturns[redacted]),browser_extract(page text, field values, network bodies) and action results. A page that prints "Signed in as you@example.com" reads as "Signed in as [redacted]". - Every screenshot is masked before it reaches the agent: password, card and one-time-code fields, username and email fields, and any saved value shown as page text.
For sites a saved login cannot fill (single sign-on, passkeys, a CAPTCHA, a code sent by email), sign in by hand once:
uvx ascended-browser signin https://example.com/login # opens the browser; sign in, then press Enter
The cookies stay in the browser profile that every later agent session starts from. Close running agent sessions first, so the sign-in lands in the saved profile rather than a session's copy.
The vault is logins.db in the data directory, readable only by your user,
and not encrypted (like gh or aws credentials files). The scrubbing and
masking cover what the browser tools return. An agent that also has a
shell or file tools (Claude Code, Codex) runs as you and can read any file you
can, this one included. Deny its file tools the path (in Claude Code,
"deny": ["Read(~/.local/share/ascended/**)"] under permissions in
~/.claude/settings.json) and keep shell commands on approval; an agent free
to run any command can still reach the file. Values shorter than 4 characters
are not scrubbed, and a value the page changes (the last four digits of a
card, say) is not matched.
Settings
| Variable | Default | |
|---|---|---|
ASCENDED_BROWSER_WINDOW |
hidden | show opens a visible window |
ASCENDED_DATA_DIR |
~/.local/share/ascended/browser |
Browser profile (sign-ins persist), saved logins (logins.db), session files |
ASCENDED_RESULT_MAX_CHARS |
24000 |
Longer results are clipped with an evidence_ref |
ASCENDED_SETTING_<KEY> |
Any browser setting, e.g. ASCENDED_SETTING_BROWSER_WORKSPACE_OBSERVE_FORMAT=outline |
|
ASCENDED_LOG_LEVEL |
WARNING |
Logs go to stderr |
Limits
- Window resizing (
browser_viewportphone/tablet/desktop presets or any width and height) works on Linux: on the package's own virtual display by default, or on your X11 display withASCENDED_BROWSER_WINDOW=show. On macOS and Windows the window keeps its launch size; emulation (dark mode, reduced motion, forced colors, offline) works everywhere. Screenshot grids across several sizes in one call are not included. - Schema-shaped extraction (a model reads the page into your JSON shape) is an Ascended app feature that needs a model, so it is not in this package and its parameters are not exposed. Everything listed under Tools runs without a model.
- One server process is one browser session: tabs and refs last until your client disconnects; the profile (cookies, sign-ins) lasts across sessions. Several sessions can run at once: the first one uses the saved profile, and any other one started while it runs gets its own copy, already signed in to whatever the saved profile was. Sign-ins made in a copy end with that session.
How it is built
src/ascended_browser/_app is generated from my Ascended app by
scripts/sync_from_ascended.py: the browser modules taken unchanged, the
browser tool dispatcher and result formatter extracted by reachability, and
every import of the rest of the app rewritten to runtime/ (small standalone
stand-ins). The sync refuses any app import it cannot map.
Tested with Ascended's own stress harnesses run against this package
(tests/stress/), a client-side MCP smoke test (tests/smoke_mcp.py), and
live-website tasks given to real agents (tests/agents/). Saved logins have
their own: tests/test_logins.py (the vault CLI and the scrubber),
tests/login_redaction_mcp.py (a real client signs in on a page that echoes
the login into its text, DOM and network, and no tool may show it; with
tesseract installed it also reads the screenshots) and
tests/signin_persists.py.
What has been verified so far: Linux (Python 3.11, 3.12 and 3.14), with Claude Code and Codex (0.160) on live-site tasks, opencode on a navigation task, and the npm launcher through uvx and through its own venv. macOS and Windows should work headless or with a visible window, but are untested.
License
MIT. The bundled axe-core (_app/browser_vendor/axe-core) is MPL-2.0 and keeps
its notice in the file.
ascended-browser MCP 질문
ascended-browser MCP는 어떤 도구를 제공하나요?
11개 도구를 제공합니다. 예: browser_open, browser_observe, browser_act, browser_extract, browser_screenshot.
에이전트가 저장된 비밀번호를 볼 수 있나요?
아니요, 에이전트는 비밀번호 값을 절대 볼 수 없습니다. 도구 결과에서 저장된 모든 사용자 이름, 비밀번호 및 TOTP 비밀 정보는 삭제됩니다.
Python을 사용하여 어떻게 설치하나요?
uvx를 사용하여 machine 상태를 확인하는 doctor 명령어를 실행하거나, 브라우저를 다운로드하는 fetch 명령어를 사용할 수 있습니다.
이것이 회귀 테스트(regression tests)를 대체할 수 있나요?
아니요, 이 도구는 결정론적인 회귀 테스트나 CI 통합보다는 에이전트 기반의 탐색적 QA를 위해 설계되었습니다.