Browser Control

Created By

adityasasidhar6 months ago

Stop feeding your agent raw HTML. BrowserControl gives LLMs true visual grounding with Set of Marks (SoM), letting them click exactly what they see without hallucinating selectors. With built-in developer tools, session recording, and persistent logins, it transforms web automation from a brittle guessing game into a reliable, human-like capability. Give your agent eyes, not just code.

# browser-control

# browser-automation

Overview Content Tools Comments

Overview

What is BrowserControl?

BrowserControl is a vision-first browser control tool designed for AI agents, enabling them to interact with web pages in a human-like manner without relying on HTML scraping or DOM guessing.

How to use BrowserControl?

To use BrowserControl, set up the MCP server and utilize commands to navigate and interact with web pages using numbered elements instead of traditional selectors.

Key features of BrowserControl?

Vision-first interaction with fully rendered web pages.
Persistent browser sessions that maintain login states and history.
Built-in developer tools for debugging and performance metrics.
Session recording for replay and inspection.
Zero extra AI cost with no external calls required.

Use cases of BrowserControl?

Autonomous web research.
Automated form filling.
End-to-end testing of web applications.
Debugging browser-based applications.
Agent-driven quality assurance workflows.

FAQ from BrowserControl?

Can BrowserControl work offline?

Yes! BrowserControl operates fully offline without needing external vision APIs.

Is BrowserControl suitable for production use?

Yes! It is production-ready and actively developed with a stable status.

What programming language is used?

BrowserControl is built with Python 3.11 and utilizes Playwright for browser automation.

Try in Playground

Server Config

{
  "mcpServers": {
    "browsercontrol": {
      "command": "python",
      "args": [
        "-m",
        "browsercontrol"
      ]
    }
  }
}

Project Info

Created At

6 months ago

Updated At

6 months ago

Author Name

adityasasidhar

Star

Language

License

Recommend Servers

10 days ago

10 days ago

Framelink Figma MCP Server

@GLips

MCP server to provide Figma layout information to AI coding agents like Cursor

TypeScript

a year ago

Framesail AI

@framesail

Official remote MCP server for Framesail AI. Create long-form (faceless YouTube) videos end to end from any MCP client: script, locked character references, storyboard, voiceover, and final video editing — with characters and style held consistent across every shot. Making long-form AI video today means 8+ tabs stitched by hand — an LLM for the script, a voice model, an image model, a video model — with characters drifting between tools and style resetting at every export. Framesail replaces the patchwork: the whole pipeline runs in one place and manages your video's context end to end. Six stages: Style (paste images, videos, or YouTube links and Framesail reverse-engineers the look, voice, and direction), Script (write it yourself or generate it in your narrative style), Reference images (auto-generated for every character, place, and prop), Voiceover (one narrator or many characters, with word-level timing), Storyboard (planned scene by scene), and Editor (captions, music, SFX, then export). No black box: you control every prompt, asset, model, and setting.

10 days ago

EdgeOne Pages MCP

@TencentEdgeOne

An MCP service designed for deploying HTML content to EdgeOne Pages and obtaining an accessible public URL.

TypeScript

a year ago

Serper MCP Server

@garymengcom

A Serper MCP Server

Python

a year ago

Frontrun

@jongall45

VC follow intelligence for AI agents. Track what top investors follow on X — detect new follows, convergence signals, and trending companies before they're announced.

5 days ago

10 days ago

A Model Context Protocol (MCP) server that integrates with Jina AI Search Foundation APIs.

JavaScript

a year ago

New Zealand Payments Mcp

10 days ago

10 days ago

10 days ago

Lithuania Payments Mcp

@junter1989k-ai

10 days ago

Kazakhstan Payments Mcp

@junter1989k-ai

10 days ago

ShareMyPage

@Henning Witzel-Acikgöz

Host the HTML or Markdown pages your AI generates and share each as a link with comments, versioning, and access control. Create, update, and organize pages and read reviewer comments over MCP.

10 days ago

10 days ago

10 days ago

10 days ago

Persistent Adaptive Planning Intelligence - structured loop engineering for AI coding assistants, with memory that persists across sessions, tools, and teammates.

10 days ago

10 days ago

10 days ago

Ivory Coast Payments Mcp

@junter1989k-ai

10 days ago

Xiangguangyu Skills

@Chromatic0618

5 AI skills as MCP tools: MBTI relationship sandbox (2-20 people), fact-checking (3 methods: source-tracing, cross-reference, logic-check), deep business analysis (5-layer), game audio brief generator, weekly skill radar. All monetized via Alipay AI Pay (¥0.10-0.50/call).

10 days ago

Search1API

One API for Search, Crawling, and Sitemaps

a year ago

Qiniu MCP Server

@Qiniu

基于七牛云产品构建的 Model Context Protocol (MCP) Server，支持用户在 AI 大模型客户端的上下文中通过该 MCP Server 来访问七牛云存储资源、利用 Dora 服务进行图片操作等。如果有什么需求欢迎在下方评论，您也可以在 github 仓库中提 issue。

Python

a year ago

Howtocook Mcp

@worryzyy

基于Anduin2017 / HowToCook （程序员在家做饭指南）的mcp server，帮你推荐菜谱、规划膳食，解决“今天吃什么“的世纪难题； Based on Anduin2017/HowToCook (Programmer's Guide to Cooking at Home), MCP Server helps you recommend recipes, plan meals, and solve the century old problem of "what to eat today"

a year ago

10 days ago

GBOX provides environments for AI Agents to operate computer and mobile devices. Mobile Scenario: Your agents can use GBOX to develop/test android apps, or run apps on the Android to complete various tasks(mobile automation). Desktop Scenario: Your agents can use GBOX to operate desktop apps such as browser, terminal, VSCode, etc(desktop automation). MCP: You can also plug GBOX MCP to any Agent you like, such as Cursor, Claude Code. These agents will instantly get the ability to operate computer and mobile devices.

a year ago

Tanzania Payments Mcp

@junter1989k-ai

10 days ago

Perplexity Ask MCP Server

@ppl-ai

A Model Context Protocol Server connector for Perplexity API, to enable web search without leaving the MCP ecosystem.

JavaScript

a year ago