adityasasidhar/browsercontrol
BrowserControl is an MCP server that gives your AI agent full browser access with a vision-first approach inspired by Google's AntiGravity IDE.
Implements a "Set of Marks" (SoM) annotation system that overlays numbered boxes on interactive elements, eliminating the need for CSS selectors or XPath parsing. Operates as an MCP-compatible server with persistent browser sessions, full JavaScript execution support, and integrated DevTools access—connecting seamlessly to Claude Desktop, Cursor, Continue.dev, and other AI IDEs via stdio transport. Provides specialized tools for file uploads, cookie management, multi-tab control, and session recording that go beyond standard DOM automation.
Available on PyPI.
Stars
7
Forks
2
Language
Python
License
MIT
Category
Last pushed
Mar 11, 2026
Monthly downloads
97
Commits (30d)
0
Dependencies
4
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/agents/adityasasidhar/browsercontrol"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Related agents
alibaba/page-agent
JavaScript in-page GUI agent. Control web interfaces with natural language.
CloakHQ/CloakBrowser
Stealth Chromium that passes every bot detection test. Drop-in Playwright replacement with...
hanzili/hanzi-browse
let any ai agent use the local browser
4ier/neo
Turn any web app into an API. Chrome extension captures browser traffic, auto-generates schemas,...
nicobailon/surf-cli
The CLI for AI agents to control Chrome. Zero config, agent-agnostic, battle-tested.