Skip to main content
Glama
Sign In
deenesjakoruzh
agent-browser

agent-browser

by Nirmalraj10567
OverviewSchemaSourceRelated ServersDiscussionsAdmin
TypeScript
Hybrid

Agent Browser MCP Server

AI 어시스턴트를 위한 브라우저 자동화 도구를 제공하기 위해 agent-browser를 래핑하는 MCP(Model Context Protocol) 서버입니다. stdio 및 HTTP/SSE 전송을 모두 지원합니다.

기능

다음을 포함한 40개 이상의 브라우저 자동화 도구:

카테고리

도구

탐색

browser_open, browser_navigate, browser_close

상호작용

browser_click, browser_fill, browser_type, browser_press, browser_hover, browser_select, browser_scroll

검사

browser_snapshot, browser_screenshot, browser_read, browser_get, browser_find

실행

browser_eval, browser_batch, browser_wait

상태

browser_cookie, browser_storage, browser_state, browser_session, browser_tab

DevTools

browser_console, browser_trace, browser_network, browser_react, browser_vitals, browser_a11y

고급

browser_frame, browser_stream, browser_dialog, browser_diff, browser_chat, browser_profile

시스템

browser_install, browser_doctor, browser_skills, browser_set

Related MCP server: selenium-mcp

설치

npm install
npm run build

사용법

Stdio 모드(로컬 MCP 클라이언트용)

npm run dev

HTTP/SSE 모드(원격 액세스용)

node server.js

서버는 기본적으로 포트 5888에서 수신 대기합니다.

환경 변수

변수

기본값

설명

PORT

5888

서버 포트

AGENT_BROWSER_SCREENSHOT_DIR

./screenshots

저장된 스크린샷 디렉터리

BASE_URL

/screenshots

스크린샷의 공개 URL 경로

MCP_SCRIPT_PATH

./dist/index.js

컴파일된 MCP 서버 경로

ENABLE_HTTPS

false

Let's Encrypt 인증서로 HTTPS 활성화

CERT_PATH

/etc/letsencrypt/live/test2.infinitrocyber.com

SSL 인증서 경로

Docker

docker build -t agentbrowser-mcp .
docker run -p 5888:5888 agentbrowser-mcp

배포

Render

render.yaml 블루프린트가 포함되어 있습니다. 저장소에서 직접 배포하세요.

PM2

pm2 start ecosystem.config.cjs

API 엔드포인트

메서드

경로

설명

GET

/health

상태 확인

GET

/mcp

SSE 연결(새 세션 생성)

POST

/mcp

JSON-RPC 요청

GET

/

서비스 정보

클라이언트 구성

Claude Desktop

{
  "mcpServers": {
    "agent-browser": {
      "command": "node",
      "args": ["dist/index.js"]
    }
  }
}

원격 HTTP 클라이언트

{
  "mcpServers": {
    "agent-browser": {
      "url": "https://your-domain.com/mcp"
    }
  }
}

라이선스

MIT

Available Tools

39 tools
browser_a11yD

Accessibility audit

Inputs: url, json, tags, session, +1 more.

browser_batchC

Execute multiple commands

Inputs: commands (required), bail.

browser_chatD

Natural language browser control

Inputs: instruction (required), session.

browser_clickC

Click element by selector or @ref

Inputs: selector (required), session.

browser_closeC

Close browser

Inputs: all, session.

browser_consoleC

View/clear console logs and errors

Inputs: action (required), json, session.

browser_cookieD

Manage cookies

Inputs: action (required), name, value, session.

browser_dialogD

Handle dialogs

Inputs: action (required), text, session.

browser_diffC

Diff snapshots/screenshots

Inputs: type (required), json, target, session, +2 more.

browser_doctorD

Diagnose install

Inputs: fix, offline.

browser_evalD

Execute JavaScript

Inputs: script (required), session.

browser_fillC

Clear and fill input

Inputs: text (required), selector (required), session.

browser_findC

Find elements semantically

Inputs: type (required), value (required), action (required), name, +1 more.

browser_frameD

Switch frame

Inputs: session, selector.

browser_getC

Get text/html/value/url/title

Inputs: property (required), session, selector.

browser_hoverD

Hover element

Inputs: selector (required), session.

browser_installC

Install Chrome

Inputs: deps.

browser_navigateC

Back/forward/reload

Inputs: direction (required), session.

browser_networkD

Network requests/routes

Inputs: action (required), url, body, type, +7 more.

browser_openC

Open URL in browser

Inputs: url (required), session.

browser_pressC

Press key (Enter, Tab, etc)

Inputs: key (required), session.

browser_profileD

Chrome profiles

Inputs: action (required), name.

browser_reactD

React devtools

Inputs: action (required), json, fiberId, session.

browser_readC

Read page content or fetch URL

Inputs: url, filter, session.

browser_screenshotD

Take screenshot

Inputs: full, path, session.

browser_scrollC

Scroll page

Inputs: direction (required), pixels, session, selector.

browser_selectC

Select dropdown option

Inputs: value (required), selector (required), session.

browser_sessionD

Session management

Inputs: action (required), scope, prefix.

browser_setC

Set viewport/device/geo/media

Inputs: value (required), setting (required), session.

browser_skillsD

List/get skills

Inputs: action (required), all, name.

browser_snapshotC

Get accessibility tree with refs

Inputs: session.

browser_stateC

Save/load auth state

Inputs: action (required), path, session.

browser_storageC

Manage localStorage/sessionStorage

Inputs: type (required), action (required), key, value, +1 more.

browser_streamD

WebSocket streaming

Inputs: action (required), port, session.

browser_tabD

Manage tabs

Inputs: action (required), url, label, target, +1 more.

browser_traceC

Record trace

Inputs: action (required), path, session.

browser_typeC

Type text into input

Inputs: text (required), selector (required), session.

browser_vitalsD

Web Vitals metrics

Inputs: url, json, session.

browser_waitC

Wait for element/text/URL

Inputs: url, text, session, timeout, +1 more.

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

    Deploy Server
    One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

    TDQS

    C2.4/5.0

    Scored across 39 tools

    Disambiguation5/5

    Each tool targets a distinct browser operation (e.g., click, fill, hover, scroll) with no overlapping responsibilities. Even similar tools like get and read are differentiated by specific data returning or page fetching, and snapshot is distinct from screenshot.

    Naming Consistency5/5

    All tools follow a consistent 'browser_<verb>' pattern (e.g., open, click, fill, type, press), with no mixed conventions or vague names. The naming is predictable and clearly conveys each tool's action.

    Tool Count2/5

    With 39 tools, the count exceeds the typical range and feels heavy for most workflows. While the browser automation domain is broad, many tools are granular (e.g., browser_console, browser_trace), leading to potential selection overhead.

    Completeness4/5

    The tool set covers a comprehensive range of browser interactions: navigation, element actions, state management, debugging, performance monitoring, and network control. Minor gaps exist (e.g., file upload, form submission explicit handling), but most core workflows are well-supported.

    Maintenance

    ActivityStale
    ResponsivenessNo recent community issues

    Resources

    Related MCP Connectors

    Related MCP Servers

    • openmcp

      openmcp-pro
      A
      license
      Not graded
      quality
      D
      maintenance
      Enables AI agents to automate web tasks such as browsing, clicking, typing, and taking screenshots via the Model Context Protocol.
      1
      MIT

    • Playwright Automation MCP

      devqa07
      A
      license
      A
      quality
      D
      maintenance
      Enables AI-powered browser automation controlled through natural language, integrating Playwright with the Model Context Protocol to perform web interactions like navigation, form filling, and screenshots.
      10
      MIT