humanized-browser
This MCP server enables natural, humanized control of a real Chrome browser from Cursor agents, simulating natural mouse paths, typing cadence, and scroll pauses for click, type, scroll, and navigate actions via a Chrome extension.
README
Humanized Browser
Operate your real Chrome browser in a humanized way from Cursor: natural mouse paths, typing cadence, and scroll pauses — so everyday tasks feel like a person, not a bot.
Architecture
User (Cursor Agent)
→ MCP stdio (packages/mcp-server)
→ WebSocket 127.0.0.1:19501
→ Chrome extension (packages/extension)
→ Humanized click / type / scroll / navigate
| Layer | Role |
|---|---|
| Cursor Agent | Plans the task and calls tools |
| MCP server | Tool surface, pairing token, localhost WS hub |
| Chrome extension | Snapshot + humanized execution on your tabs |
We do not rebuild a daily LLM agent loop — Cursor is the brain. This repo is the hand.
Prerequisites
- Node.js 20+
- pnpm 9+ (
npm install -g pnpm) - Google Chrome (or Chromium)
- Cursor with Agent / MCP enabled
Setup
1. Install & build
pnpm install
pnpm build
2. Load the extension
- Open
chrome://extensions - Enable Developer mode
- Load unpacked → select
packages/extension/dist - Keep the extension enabled
3. Pair with the MCP server
When Cursor starts the MCP server it writes:
~/.humanized-browser/credentials.json—{ token, port }- Token also printed on stderr of the MCP process
Open the Humanized Browser popup → paste token → set port (default 19501) → Connect.
Badge shows ON when connected.
4. Cursor MCP config
Project config is already at .cursor/mcp.json (absolute path to the built MCP entry). After pnpm build, reload MCP in Cursor (Settings → MCP), or restart Cursor.
If you move the repo, update the args path in .cursor/mcp.json accordingly.
Tools
| Tool | Purpose |
|---|---|
browser_status |
Extension online? |
tabs_list |
List tabs |
navigate |
Open URL (humanized pause after load) |
snapshot |
Compressed page tree + refs |
click |
Bezier mouse path + jitter |
type |
Variable key delays |
scroll |
Humanized scroll / scroll-into-view |
wait |
Delay or wait for selector/ref |
screenshot |
Viewport capture (prefer snapshot for actions) |
Example prompt (in Cursor Agent)
Use humanized-browser tools: open https://example.com, snapshot the page, and click the “More information…” link if present.
Humanize defaults
Humanized timing is on by default. Popup Fast mode skips delays for debugging only — do not use it for real sites you care about.
Security
- WebSocket hub binds to 127.0.0.1 only
- Extension must present the pairing token
- No remote browser control in this MVP
Packages
packages/shared— protocol + humanize helperspackages/mcp-server— MCP stdio + WS hubpackages/extension— MV3 execution plane
End-to-end checklist
pnpm buildsucceeds- Extension loads from
packages/extension/distwithout errors - Cursor MCP shows
humanized-browserconnected - Popup Connect → status
connected/ badgeON - In Agent: call
browser_status→ connected navigate→snapshot→click/typewith visible humanized motion
Out of scope (later)
- Cursor SDK headless runner
- Native Messaging instead of WS
- Domain allowlists / recording
推荐服务器
Baidu Map
百度地图核心API现已全面兼容MCP协议,是国内首家兼容MCP协议的地图服务商。
Playwright MCP Server
一个模型上下文协议服务器,它使大型语言模型能够通过结构化的可访问性快照与网页进行交互,而无需视觉模型或屏幕截图。
Magic Component Platform (MCP)
一个由人工智能驱动的工具,可以从自然语言描述生成现代化的用户界面组件,并与流行的集成开发环境(IDE)集成,从而简化用户界面开发流程。
Audiense Insights MCP Server
通过模型上下文协议启用与 Audiense Insights 账户的交互,从而促进营销洞察和受众数据的提取和分析,包括人口统计信息、行为和影响者互动。
VeyraX
一个单一的 MCP 工具,连接你所有喜爱的工具:Gmail、日历以及其他 40 多个工具。
graphlit-mcp-server
模型上下文协议 (MCP) 服务器实现了 MCP 客户端与 Graphlit 服务之间的集成。 除了网络爬取之外,还可以将任何内容(从 Slack 到 Gmail 再到播客订阅源)导入到 Graphlit 项目中,然后从 MCP 客户端检索相关内容。
Kagi MCP Server
一个 MCP 服务器,集成了 Kagi 搜索功能和 Claude AI,使 Claude 能够在回答需要最新信息的问题时执行实时网络搜索。
e2b-mcp-server
使用 MCP 通过 e2b 运行代码。
Neon MCP Server
用于与 Neon 管理 API 和数据库交互的 MCP 服务器
Exa MCP Server
模型上下文协议(MCP)服务器允许像 Claude 这样的 AI 助手使用 Exa AI 搜索 API 进行网络搜索。这种设置允许 AI 模型以安全和受控的方式获取实时的网络信息。