How do I use browser-mcp?

1. Click on "Install Server". 2. Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state. 3. In the chat, type @ followed by the MCP server name and your instructions, e.g., "@browser-mcp Open example.com, take a snapshot, then click the login link and screenshot the result." That's it! The server will respond to your query, and you can continue using it as needed. Here is a step-by-step guide with screenshots.

browser-mcp

by jixingyu999

Overview Schema Related Servers Score Discussions

JavaScript

Local

browser-mcp

License: MIT Node MCP Playwright

一个为 AI 而设计的浏览器操作 MCP 服务器：22 个工具，让 AI 像人一样浏览、点击、输入、截图网页——不需要手写选择器。针对办公自动化场景做了专项优化：批量填表、数据提取、文件下载、PDF 存档、页面监控。

为什么是它

市面上大多数浏览器 MCP 要求 AI 写 CSS 选择器，这是 AI 操作网页失败的头号原因。browser-mcp 采用 ref 编号体系：

AI: browser_snapshot
←  [e1] <a> More information -> /about
   [e2] <input type=search> (搜索)
   [e3] <button> 登录

AI: browser_click { "ref": "e3" }     ← 点击"登录"，指哪打哪
✓  已点击：e3

snapshot 一次，拿到全部可交互元素的编号，之后所有操作只用 ref。元素找不到时，错误信息还会附带当前页面状态摘录，AI 能自行纠错重试，而不是瞎猜。

Related MCP server: atlas-browser-mcp

特性

ref 编号体系 — 快照给可交互元素编号，点击/输入/选择全部支持 ref 定位，AI 无需写选择器
智能等待 — 导航、点击后自动等待网络空闲（最多 4s），大幅减少手动 wait
登录态持久化 — cookie/localStorage 保存到磁盘（storageState），重启免重新登录
错误自解释 — 操作失败时返回当前 URL + 页面文本摘录 + 修复建议
办公自动化专项 — 批量填表、表格/列表数据提取（JSON/CSV）、文件下载落盘、页面 PDF 存档、后台变化监控
多浏览器回退 — Chromium → Edge → Chrome 依次尝试，Windows 无需下载浏览器即可使用
零构建 — 纯 ESM 单文件，node index.mjs 直接跑

演示

AI 通过 MCP 协议真实打开 example.com、识别元素、点击链接跳转：

demo

快速开始

git clone https://github.com/jixingyu999/browser-mcp.git
cd browser-mcp
npm install
npm test        # 端到端测试：真实打开网页、ref 点击、截图

接入 MCP 宿主（Claude Desktop / Cursor / WorkBuddy 等）

在宿主的 MCP 配置文件中添加：

{
  "mcpServers": {
    "browser-mcp": {
      "command": "node",
      "args": ["/path/to/browser-mcp/index.mjs"],
      "env": {
        "BROWSER_MCP_HEADLESS": "0",
        "BROWSER_MCP_STORAGE_STATE": "/path/to/browser-mcp/storage.json"
      }
    }
  }
}

环境变量

变量	默认值	说明
`BROWSER_MCP_HEADLESS`	`1`	设为 `0` 显示浏览器窗口，便于观察 AI 操作
`BROWSER_MCP_OUTPUT_DIR`	系统临时目录	截图输出目录
`BROWSER_MCP_STORAGE_STATE`	（空）	登录态文件路径，配置后自动加载/保存
`BROWSER_MCP_TIMEOUT`	`10000`	默认操作超时（毫秒）

工具列表（22 个）

工具	说明
`browser_navigate`	打开 URL，自动补全协议前缀，完成后等待网络空闲
`browser_snapshot`	获取页面结构 + 可交互元素 ref 编号列表（核心工具）
`browser_click`	点击元素：`ref` 优先，兼容 CSS / `text=` / `role=`
`browser_type`	输入文字：ref 定位，可选清空、回车提交
`browser_press_key`	发送按键（Enter / Escape / Control+A …）
`browser_screenshot`	截图，返回图片数据并保存文件
`browser_get_text`	获取页面或指定元素的文本
`browser_evaluate`	在页面上下文执行 JavaScript
`browser_scroll`	上/下滚动
`browser_select_option`	选择下拉框选项
`browser_wait`	等待毫秒 / 元素出现 / 文本出现
`browser_back`	后退
`browser_list_tabs`	列出所有标签页
`browser_tab`	新建 / 切换标签页
`browser_save_state`	手动保存登录态
`browser_fill_form`	专项：一次填完整个表单（文本/勾选/下拉混合，可自动提交）
`browser_extract_table`	专项：提取 `<table>` 为 JSON/CSV，可保存文件
`browser_extract`	专项：按容器+字段映射抓取列表数据（JSON/CSV）
`browser_download`	专项：点击触发下载并自动保存到输出目录
`browser_pdf`	专项：页面保存为 PDF 存档（无头模式）
`browser_watch`	专项：后台轮询监控页面变化（selector/text/JS 三种模式）
`browser_close`	关闭浏览器（自动保存登录态）

办公自动化专项

针对日常工作中最繁琐的重复流程，提供一站式工具：

场景	工具组合	效果
填写报名/审批/申请表单	`browser_fill_form`	一次调用填完文本、勾选、下拉全部字段，自动提交
扒取后台数据/报表	`browser_extract_table` / `browser_extract`	表格、列表一键转 JSON/CSV 并落盘，CSV 转义正确处理
导出对账单/发票	`browser_download`	点击导出按钮自动等待下载并保存
网页存档留证	`browser_pdf`	页面转 A4 PDF 存档
盯库存/价格/审批状态	`browser_watch`	后台轮询监控，随时 check 是否变化

示例：把后台报表自动存档

1. browser_navigate        后台地址（登录态已持久化，免登录）
2. browser_fill_form       { fields: [{ref:"e3", value:"2026-09"}, {ref:"e5", value:true}], submitRef: "e6" }
3. browser_extract_table   { format: "csv", save: true, filename: "9月报表.csv" }
4. browser_pdf             { filename: "9月报表存档.pdf" }

典型用法（AI 工作流）

1. browser_navigate  https://example.com
2. browser_snapshot                       → 拿到元素 ref 列表
3. browser_type      { ref: "e2", text: "关键词", submit: true }
4. browser_click     { ref: "e3" }        → 点击搜索按钮
5. browser_screenshot                     → 截图查看结果
6. browser_get_text  { selector: "body" } → 提取结果文本

架构

AI 宿主（Claude Desktop / Cursor / WorkBuddy）
    │  MCP 协议（stdio / JSON-RPC）
    ▼
browser-mcp（Node.js，@modelcontextprotocol/sdk）
    │  Playwright API
    ▼
Chromium / Edge / Chrome（自动回退）

Roadmap

网络嗅探工具（拦截 XHR / WebSocket，直接读数据）
游戏操作套件（鼠标坐标移动、按住不放、状态轮询）
失败视觉回退（选择器失败自动截图，AI 视觉定位）
操作轨迹回放（Playwright trace 生成）

License

MIT © jixingyu999

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections. Dates show when Glama detected each change.

No tool schema history has been recorded yet.

This server cannot be installed

RayrunBuild, deploy, and operate MCP servers without becoming an infrastructure team.ray.runAd

Maintenance

ActivityMaintained

ResponsivenessNo issues

Resources

Need Help?

Related Servers

Unclaimed servers have limited discoverability.

Looking for Admin?

If you are the server author, to access and configure the admin panel.

Related MCP Connectors

SkyvernOAuth
io.github.Skyvern-AI
AI-powered browser automation — navigate, click, fill forms, and extract data from any website.
Browser Automation Web Scraping App Automation
222,930
TinyFish AI Web AgentOAuth
ai.mino
AI-powered web automation. Navigate websites using AI agents for one page or a thousand
Browser Automation Autonomous Agents Web Scraping
2
TinyFish AI Web AgentOAuth
ai.tinyfish.agent
AI-powered web automation. Navigate websites using AI agents for one page or a thousand
Browser Automation Agent Orchestration Web Scraping
2
Manifest B
io.omfang
Turn any webpage into a structured action manifest — clickable, fillable, submittable elements.
Browser Automation Web Scraping
12

Related MCP Servers

MCP Browser Use Server
Browser Automation Agent Orchestration
JovaniPink
A
license
Not graded
quality
C
maintenance
Enables AI agents to interact with web browsers using natural language, featuring automated browsing, form filling, vision-based element detection, and structured JSON responses for systematic browser control.
Updated 15 days ago (2026-08-22 18:27 UTC)
62
MIT
atlas-browser-mcp
Browser Automation Web Scraping Autonomous Agents
LingTravel
A
license
A
quality
D
maintenance
Enables AI agents to navigate the web visually using screenshot-based interaction and Set-of-Mark labeling for interactive elements. It supports humanized browsing behaviors, anti-detection measures, and complex tasks like multi-click CAPTCHA solving.
Updated 9 months ago (2025-12-13 15:59 UTC)
6
MIT
Cloudflare Playwright MCP
Browser Automation Web Scraping
erikzrekz
F
license
Not graded
quality
C
maintenance
Enables AI assistants to control a browser for web automation tasks like navigation, typing, clicking, and taking screenshots.
Updated a year ago (2025-10-14 16:33 UTC)
-
Cloudflare Playwright MCP
Browser Automation Web Scraping
Abuh112
F
license
Not graded
quality
C
maintenance
Enables AI assistants to control a browser for web automation tasks such as navigation, typing, clicking, and taking screenshots.
Updated 6 months ago (2026-02-24 05:02 UTC)
-

Latest Blog Posts

Who's Calling? MCP Hosts Are an Identity Blind Spot (And the Spec Knows It)
By Om-Shree-0709 on July 25, 2026.
mcp
Agent Identity
OAuth 2.1
Your AI Chatbot Just Exposed Your CEO's Salary to an Intern
By Om-Shree-0709 on July 2, 2026.
Agent Identity
MCP Security
OAuth Delegation
Why MCP Servers Need Execution Sandboxing (And Why Your Current Stack Isn't Enough)
By Om-Shree-0709 on June 30, 2026.
Agentic Ai
Prompt Injection
WebAssembly

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/jixingyu999/browser-mcp'

If you have feedback or need assistance with the MCP directory API, please join our Discord server

browser-mcp

为什么是它

特性

演示

快速开始

接入 MCP 宿主（Claude Desktop / Cursor / WorkBuddy 等）

环境变量

工具列表（22 个）

办公自动化专项

典型用法（AI 工作流）

架构

Roadmap

License

Tool Schema Changelog

Maintenance

Resources

Looking for Admin?

Related MCP Connectors

Related MCP Servers

MCP Browser Use Server

atlas-browser-mcp

Cloudflare Playwright MCP

Cloudflare Playwright MCP

Latest Blog Posts

MCP directory API